70 agents. 3 stops are yours.
Every card below is read from this repo's own pipeline map and gate rules, not hand-written. See what runs for your project, and where you get to say no.
9 agents on the main path. 3 stops are yours.
-
The first agent in the pipeline — runs BEFORE architect. Turns a raw idea or problem statement into a validated product brief. Frames the problem, brainstorms options, runs a multi-LLM idea debate (4 personas on 4 models), and synthesizes a recommendation the CTO approves at gate:product (the one human gate — WHAT before HOW). Outputs docs/product/BRIEF-{slug}.md + discovery-summary for architect.
-
Use when starting any new feature. Creates architecture docs, ADRs, cost estimates, Well-Architected review. Always first in the pipeline.
-
Use after architect produces the ARCH doc. Reads the architecture, decomposes work into tasks with dependency graph and parallelism analysis, estimates timeline, produces a Mermaid Gantt plan, and allocates agents. Creates gate:plan for human approval before any senior-dev starts.
-
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
-
Use after senior-dev completes a task and before gate:ship. One stable, human-grade reviewer (correctness, security, performance, readability) — replaces ad-hoc inline review forks. Reads the diff, files bugs in Beads, emits a verdict.
-
Use after senior-dev completes implementation. Analyzes actual code, then runs type-appropriate QA, writes report, files bugs in Beads.
-
Use after QA passes. Runs security audit by project type, writes report, controls gate:ship.
-
Use after gate:ship is approved. Deploys using the method matching the project type.
-
Production support. Monitors logs, triages incidents, creates Beads tasks. For P0 — immediate investigation + postmortem.
-
gate:productstops by default
-
gate:archstops by default
-
gate:planstops at: expert, step-by-step
-
gate:codestops at: strict, expert, step-by-step
-
gate:qastops at: expert, step-by-step
-
gate:shipstops by default
-
gate:securityalways for regulated
-
gate:compliancealways for regulated
-
gate:importnever switched off
Which gates stop at each approval level
| Level | gate:product | gate:arch | gate:plan | gate:code | gate:qa | gate:ship | gate:security | gate:compliance | gate:import |
|---|---|---|---|---|---|---|---|---|---|
| auto | — | — | — | — | — | regulated only | regulated only | regulated only | stops |
| product-only | stops | — | — | — | — | stops | regulated only | regulated only | stops |
| ship-only | — | — | — | — | — | stops | regulated only | regulated only | stops |
| gates-only (default) | stops | stops | — | — | — | stops | regulated only | regulated only | stops |
| strict | — | stops | — | stops | — | stops | regulated only | regulated only | stops |
| expert | stops | stops | stops | stops | stops | stops | stops | regulated only | stops |
| step-by-step | stops | stops | stops | stops | stops | stops | stops | regulated only | stops |
Pick your project. See who joins.
Fintech · EU
7 run · 6 stops · 2 sign-offs
| Run for this context | Slot | Source |
|---|---|---|
| architect | Main path · stage 02 | always |
| design-advisor | before senior-dev | always |
| gdpr-reviewer | before senior-dev | eu |
| pci-reviewer | before senior-dev suggested when files change: src/billing/stripe-webhook.ts · api/refund.ts | always |
| qa-engineer | Main path · stage 06 | always |
| regulated-reviewer | before senior-dev suggested when files change: config/dora-ict-register.yaml · src/nis2-controls.ts | always |
| senior-dev | Main path · stage 04 | always |
- gate:product
- gate:arch
- gate:import
- gate:security
- gate:compliance
- gate:ship
gate:eu-ai-act-classification · gate:gdpr-dpia
accounting-reviewer · db-migration-reviewer · dpdpa-reviewer · tax-reviewer · us-ai-reviewer · us-privacy-reviewer
db-migration-reviewer — db/migrations/0007_add_index.sql · prisma/migrations/20260801_init/migration.sql
pci-reviewer — src/billing/stripe-webhook.ts · api/refund.ts
accounting-reviewer — src/journal-entry.ts · lib/general-ledger.ts
tax-reviewer — src/form-8879.ts · lib/tax-prep.py
regulated-reviewer — config/dora-ict-register.yaml · src/nis2-controls.ts
51 other agents are not in this team.
Healthcare · US-CA
7 run · 6 stops · 2 sign-offs
| Run for this context | Slot | Source |
|---|---|---|
| architect | Main path · stage 02 | always |
| design-advisor | before senior-dev | always |
| healthcare-reviewer | before senior-dev suggested when files change: src/hipaa-audit.ts · integrations/fhir/client.ts | always |
| qa-engineer | Main path · stage 06 | always |
| security-officer | Main path · stage 07 | always |
| senior-dev | Main path · stage 04 | always |
| us-privacy-reviewer | before senior-dev | us-ca |
- gate:product
- gate:arch
- gate:import
- gate:security
- gate:compliance
- gate:ship
gate:ccpa-dsrp · gate:us-state-privacy-matrix
gdpr-reviewer · rcm-reviewer · us-ai-reviewer
security-officer — src/auth/session.ts · api/oauth-callback.ts
healthcare-reviewer — src/hipaa-audit.ts · integrations/fhir/client.ts
rcm-reviewer — src/cms-1500.ts · lib/prior-auth.ts
55 other agents are not in this team.
Booking · routing + mobile
13 run · 4 stops · 0 sign-offs
| Run for this context | Slot | Source |
|---|---|---|
| app-scaffolder | before senior-dev | always |
| architect | Main path · stage 02 | always |
| auth-engineer | before senior-dev | always |
| design-advisor | before senior-dev | always |
| geo-routing-engineer | before senior-dev | routing |
| integrations-engineer | before senior-dev | always |
| migration-import-engineer | before senior-dev | always |
| mobile-app-builder | before code-reviewer | mobile |
| pci-reviewer | before senior-dev suggested when files change: src/billing/stripe-webhook.ts · api/refund.ts | always |
| qa-engineer | Main path · stage 06 | always |
| security-officer | Main path · stage 07 | always |
| senior-dev | Main path · stage 04 | always |
| subscription-billing-engineer | before senior-dev | always |
- gate:product
- gate:arch
- gate:import
- gate:ship
none declared for this selection
pci-reviewer — src/billing/stripe-webhook.ts · api/refund.ts
security-officer — src/auth/session.ts · api/oauth-callback.ts
51 other agents are not in this team.
The rules behind this
| Archetype | Adds | Agents |
|---|---|---|
| AI agent | ai-eval-engineer · ai-prompt-architect · ai-security-reviewer | 6 |
| AI system | ai-eval-engineer · ai-prompt-architect · ai-security-reviewer | 6 |
| Booking / scheduling | app-scaffolder · auth-engineer · design-advisor · integrations-engineer · migration-import-engineer · pci-reviewer · subscription-billing-engineer | 11 |
| Browser extension | design-advisor · web-store-reviewer | 5 |
| CLI tool | cli-reviewer | 4 |
| CMS | cms-reviewer · design-advisor | 5 |
| E-commerce | design-advisor · pci-reviewer | 6 |
| Content / media platform | app-scaffolder · auth-engineer · design-advisor · integrations-engineer · media-pipeline-engineer · migration-import-engineer · pci-reviewer · subscription-billing-engineer | 12 |
| CRM | app-scaffolder · auth-engineer · design-advisor · integrations-engineer · migration-import-engineer · subscription-billing-engineer | 10 |
| Dashboard / analytics | app-scaffolder · auth-engineer · connector-builder · design-advisor · integrations-engineer · migration-import-engineer · subscription-billing-engineer | 11 |
| Data platform | data-platform-reviewer | 4 |
| defense-govcon | cmmc-reviewer · gov-reviewer | 6 |
| Developer tool | devtools-reviewer | 4 |
| EdTech | design-advisor · edtech-reviewer | 5 |
| Enterprise SaaS | design-advisor · enterprise-saas-reviewer | 5 |
| Fintech | design-advisor · pci-reviewer · regulated-reviewer | 6 |
| Game | design-advisor · game-reviewer | 5 |
| Government | design-advisor · gov-reviewer | 6 |
| New project | regulated floor only | 3 |
| Healthcare | design-advisor · healthcare-reviewer | 6 |
| Infrastructure | infra-reviewer | 4 |
| Insurance | design-advisor · insurance-reviewer · regulated-reviewer | 6 |
| IoT / embedded | firmware-reviewer | 4 |
| Legal / Law firm | design-advisor · legal-reviewer | 6 |
| Library / SDK | library-reviewer | 4 |
| Marketplace | design-advisor · marketplace-reviewer · pci-reviewer | 6 |
| Marketplace | app-scaffolder · auth-engineer · design-advisor · integrations-engineer · migration-import-engineer · pci-reviewer · subscription-billing-engineer | 11 |
| MLOps pipeline | ai-security-reviewer · mlops-reviewer | 5 |
| Mobile app | design-advisor · mobile-store-reviewer | 6 |
| Regulated system | regulated-reviewer | 4 |
| Streaming system | streaming-reviewer | 4 |
| Vertical SaaS | app-scaffolder · auth-engineer · design-advisor · integrations-engineer · migration-import-engineer · subscription-billing-engineer | 10 |
| Web service | design-advisor | 5 |
| Web3 / DeFi | design-advisor · oracle-reviewer | 5 |
| Jurisdiction | Adds | Agents |
|---|---|---|
| EU · GDPR | gdpr-reviewer | 1 |
| US · FTC Act § 5 | us-privacy-reviewer | 1 |
| US-CA · CCPA / CPRA | us-privacy-reviewer | 1 |
| UK · UK GDPR | gdpr-reviewer | 1 |
| IN · DPDPA 2023 | dpdpa-reviewer | 1 |
| BR · LGPD | gdpr-reviewer | 1 |
| AU · Privacy Act 1988 | us-privacy-reviewer | 1 |
| SG · PDPA 2012 | us-privacy-reviewer | 1 |
| CA · PIPEDA | us-privacy-reviewer | 1 |
| JP · APPI 2022 | us-privacy-reviewer | 1 |
| CN · PIPL 2021 | gdpr-reviewer | 1 |
| KR · PIPA | us-privacy-reviewer | 1 |
| Signal | Adds | Agents |
|---|---|---|
| Voice / telephony | voice-ai-reviewer | 1 |
| Hiring | hr-ai-reviewer | 1 |
| Public API | api-platform-reviewer | 1 |
| Tracking pixels | adtech-privacy-reviewer · us-privacy-reviewer | 2 |
| AI governance | us-ai-reviewer | 1 |
| Routing / maps (archetype-gated) | geo-routing-engineer | 1 |
| Mobile / field crews (archetype-gated) | mobile-app-builder | 1 |
| Reviewer | Example paths |
|---|---|
| db-migration-reviewer | db/migrations/0007_add_index.sql · prisma/migrations/20260801_init/migration.sql |
| pci-reviewer | src/billing/stripe-webhook.ts · api/refund.ts |
| security-officer | src/auth/session.ts · api/oauth-callback.ts |
| ai-security-reviewer | prompts/system.txt · src/rag/retriever.ts |
| ai-eval-engineer | tests/eval/runner.mjs · data/golden_set.jsonl |
| mobile-store-reviewer | fastlane/Fastfile · ios/iap-manager.swift |
| api-platform-reviewer | api/openapi.yaml · src/webhooks.ts |
| voice-ai-reviewer | integrations/twilio-handler.ts · src/ivr/menu.ts |
| hr-ai-reviewer | src/hiring/rank.ts · lib/resume_screen.py |
| edtech-reviewer | src/coppa-consent.ts · lib/student_data.py |
| gov-reviewer | config/fedramp-boundary.yaml · src/fisma-controls.ts |
| game-reviewer | src/loot_box.ts · config/esrb.json |
| enterprise-saas-reviewer | src/scim/provision.ts · db/row-level-security.sql |
| procurement-reviewer | src/purchase-order.ts · lib/punchout.ts |
| accounting-reviewer | src/journal-entry.ts · lib/general-ledger.ts |
| msp-reviewer | src/rmm-agent.ts · lib/credential-vault.ts |
| tax-reviewer | src/form-8879.ts · lib/tax-prep.py |
| insurance-reviewer | src/naic-filing.ts · lib/actuarial-model.py |
| legal-reviewer | src/iolta-ledger.ts · lib/conflict-check.ts |
| healthcare-reviewer | src/hipaa-audit.ts · integrations/fhir/client.ts |
| rcm-reviewer | src/cms-1500.ts · lib/prior-auth.ts |
| regulated-reviewer | config/dora-ict-register.yaml · src/nis2-controls.ts |
| infra-reviewer | infra/main.tf · helm/values.yaml |
| web-store-reviewer | extension/manifest.json · src/mv3-worker.ts |
| performance-engineer | tests/k6/load.js · src/perf-budget.ts |
| library-reviewer | Cargo.toml · pyproject.toml |
| cli-reviewer | bin/great-cto · src/cli/main.ts |
| mcp-server-reviewer | mcp-servers/llm-router/server.py · src/mcp.ts |
Every agent — what it may touch, what it leaves behind.
Main path (9)
product-owner
The first agent in the pipeline — runs BEFORE architect. Turns a raw idea or problem statement into a validated product brief. Frames the problem, brainstorms options, runs a multi-LLM idea debate (4 personas on 4 models), and synthesizes a recommendation the CTO approves at gate:product (the one human gate — WHAT before HOW). Outputs docs/product/BRIEF-{slug}.md + discovery-summary for architect.
- Shell
- none
- Web
- yes
- Spawns agents
- yes
- Skills
- brainstorming · brainstorm [external · product-management] · writing-plans [external · superpowers]
- Produces
- brief
- Joins
- Main path · stage 01
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/product-owner.md ↗
architect
Use when starting any new feature. Creates architecture docs, ADRs, cost estimates, Well-Architected review. Always first in the pipeline.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- decision-eval · writing-plans [external · superpowers] · requesting-code-review [external · superpowers] · system-architect [external · anthropic-skills] · adr [external · anthropic-skills] · beads · skeptical-triage · done-blocked · well-architected · discovery · migration-ready-schema · stack-baseline
- Produces
- arch
- Joins
- Main path · stage 02
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/architect.md ↗
pm
Use after architect produces the ARCH doc. Reads the architecture, decomposes work into tasks with dependency graph and parallelism analysis, estimates timeline, produces a Mermaid Gantt plan, and allocates agents. Creates gate:plan for human approval before any senior-dev starts.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- pm-planning · pre-mortem · cost-model · anti-patterns · beads
- Produces
- plan · briefs
- Joins
- Main path · stage 03
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/pm.md ↗
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- test-driven-development [external · superpowers] · subagent-driven-development [external · superpowers] · requesting-code-review [external · superpowers] · beads · done-blocked · ui-ux-pro-max · stack-baseline · web-artifacts-builder [external · anthropic-skills] · theme-factory [external · anthropic-skills]
- Produces
- receipt
- Joins
- Main path · stage 04
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/senior-dev.md ↗
code-reviewer
Use after senior-dev completes a task and before gate:ship. One stable, human-grade reviewer (correctness, security, performance, readability) — replaces ad-hoc inline review forks. Reads the diff, files bugs in Beads, emits a verdict.
- Shell
- full
- Web
- no
- Spawns agents
- no
- Skills
- beads
- Produces
- receipt
- Joins
- Main path · stage 05
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/code-reviewer.md ↗
qa-engineer
Use after senior-dev completes implementation. Analyzes actual code, then runs type-appropriate QA, writes report, files bugs in Beads.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- beads · skeptical-triage · done-blocked · prose-style · test-strategy
- Produces
- report
- Joins
- Main path · stage 06
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/qa-engineer.md ↗
security-officer
Use after QA passes. Runs security audit by project type, writes report, controls gate:ship.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- cso · beads · skeptical-triage · done-blocked · prose-style
- Produces
- report
- Joins
- Main path · stage 07
suggested when files change: src/auth/session.ts · api/oauth-callback.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/security-officer.md ↗
devops
Use after gate:ship is approved. Deploys using the method matching the project type.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- ship · land-and-deploy · canary · beads · done-blocked · observability-baseline
- Produces
- not declared
- Joins
- Main path · stage 08
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/devops.md ↗
l3-support
Production support. Monitors logs, triages incidents, creates Beads tasks. For P0 — immediate investigation + postmortem.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- systematic-debugging [external · superpowers] · investigate · beads · done-blocked · observability-baseline
- Produces
- not declared
- Joins
- Main path · stage 09
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/l3-support.md ↗
Prototyper (2)
decision-scorer
Scores 2+ architectural alternatives against PROJECT.md criteria. Called by architect after proposing variants. Outputs a weighted scoring table and recommended choice.
- Shell
- none
- Web
- no
- Spawns agents
- no
- Skills
- not declared
- Produces
- not declared
- Joins
- with architect
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/decision-scorer.md ↗
design-advisor
Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs docs/design/DESIGN-{slug}.md. Plan altitude only — never writes implementation code.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- ui-ux-pro-max · anydesign · committed-aesthetic · aesthetic-instrument · writing-plans [external · superpowers] · decision-eval · beads · skeptical-triage · done-blocked
- Produces
- design
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/design-advisor.md ↗
Builder (11)
ai-eval-engineer
Builds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-*.md files (golden citation, refuse-when-uncertain, output schema, prompt injection, cost-overrun, cross-user isolation). Runs regression on every prompt or model change. Detects drift.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · test-driven-development [external · superpowers] · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: tests/eval/runner.mjs · data/golden_set.jsonl - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/ai-eval-engineer.md ↗
ai-prompt-architect
Designs and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/adr/ADR-{NN}-PROMPT-{name}.md files with sha256-pinned prompt text, jailbreak resistance test cases, and revision history. Pairs with ai-eval-engineer for golden-set scenarios.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev via ai-eval-engineer
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/ai-prompt-architect.md ↗
app-scaffolder
Project-scaffolding builder that stands up a working base application from the pinned stack-baseline so senior-dev implements FEATURES, not boilerplate. Creates the Next.js + TypeScript + Tailwind/shadcn skeleton, wires Drizzle + Postgres, Auth.js (to the auth-engineer contract), env template, folder structure, CI, and a passing smoke test — a deployable empty app. Runs first in the build, after gate:plan, before senior-dev. Writes the scaffold + docs/SCAFFOLD-{slug}.md. Without a pinned starter every build reinvents the skeleton; this makes the first hour of every product identical and correct.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- stack-baseline · migration-ready-schema · observability-baseline · test-driven-development [external · superpowers] · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/app-scaffolder.md ↗
auth-engineer
Authentication and access-control specialist for SMB Product-Builder products. Owns the auth contract — provider choice (Auth.js default / Clerk fast-path), session model, RBAC, multi-tenant row-level isolation, the protected-route map, account lifecycle (signup/login/reset/invite), and OAuth/magic-link/password flows. Runs after architect, before senior-dev. Writes docs/auth/AUTH-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- stack-baseline · migration-ready-schema · prose-style · skeptical-triage · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/auth-engineer.md ↗
connector-builder
Source-connector specialist for dashboard / analytics Product-Builder products. The read-side twin of integrations-engineer — owns the connector contract for pulling data IN from sources (Stripe, Google Analytics, QuickBooks, Google/Meta Ads, Shopify, carrier APIs): OAuth source auth, incremental sync (cursors/CDC), schema mapping into the warehouse-lite, backfill, freshness SLAs, and partial-failure handling. Runs after architect, before senior-dev. Writes docs/connectors/CONNECT-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- migration-ready-schema · prose-style · skeptical-triage · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/connector-builder.md ↗
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider selection, ETA + time-window handling, re-optimization on change, and the cost/quBudget of map API calls. Runs after architect, before senior-dev. Writes docs/routing/ROUTE-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- cost-model · prose-style · skeptical-triage · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/geo-routing-engineer.md ↗
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft Calendar, Shopify, MLS/IDX, and carrier APIs. Runs after architect/design-advisor, before senior-dev. Writes docs/integrations/INTEGRATE-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- lifecycle-messaging · prose-style · skeptical-triage · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/integrations-engineer.md ↗
media-pipeline-engineer
Media-pipeline specialist for content-platform Product-Builder products (on-demand video, coaching, online-ordering imagery, storefronts). Owns the media contract — upload, transcode/HLS/ABR, storage tiers, signed CDN delivery, image optimization (AVIF/WebP/responsive srcset), access-tier gating, and processing-job idempotency. Runs after architect/design-advisor, before senior-dev. Writes docs/media/MEDIA-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- cost-model · prose-style · skeptical-triage · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/media-pipeline-engineer.md ↗
migration-import-engineer
Data-migration and onboarding-import specialist for SMB Product-Builder archetypes. Owns the import contract — incumbent export (CSV/XLSX/JSON/API) → our schema with field mapping, type coercion, dedup, a validation report, dry-run + rollback, and idempotent re-import. Source playbooks for ServiceTitan, Toast, Mindbody, Shopify, QuickBooks, Follow Up Boss. Runs after architect, before/with senior-dev. Writes docs/data-import/IMPORT-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- vertical-onboarding · migration-ready-schema · prose-style · skeptical-triage · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/migration-import-engineer.md ↗
mobile-app-builder
React Native implementer for Product-Builder products whose users work in the field (home-services dispatch, construction field-docs, field-booking, delivery). Builds the mobile app to the design-advisor's RN contract with TDD — offline-first sync, camera/photo + location capture, push notifications, and store-submission readiness — then hands off to mobile-store-reviewer for policy sign-off. Activated when a product's design contract specifies a React Native target. Field crews live on a phone; we had a mobile-store-reviewer (policy) but no builder — this is the builder.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- test-driven-development [external · superpowers] · requesting-code-review [external · superpowers] · beads · done-blocked · ui-ux-pro-max
- Produces
- not declared
- Joins
- before code-reviewer
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/mobile-app-builder.md ↗
subscription-billing-engineer
Subscription and billing specialist for SMB Product-Builder archetypes. Owns the billing contract — Stripe Billing/Connect plans and tiers, usage metering, proration, dunning, webhook reconciliation, tax (Stripe Tax), customer portal, trial→paid, and refund/dispute hand-off. Runs after architect, before senior-dev. Writes docs/billing/BILLING-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- cost-model · prose-style · skeptical-triage · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/subscription-billing-engineer.md ↗
Sweeper (1)
e2e-test-engineer
Use after qa-engineer passes and before/around devops deploy. Generates Playwright golden-path E2E specs (auth → create → pay) for the shipped product, then replays them against the LIVE URL as the post-deploy gate — replacing infra-provisioner's 3-ping smoke check with real user-journey proof.
- Shell
- full
- Web
- no
- Spawns agents
- no
- Skills
- beads · stack-baseline
- Produces
- not declared
- Joins
- before devops
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/e2e-test-engineer.md ↗
Grower (2)
growth-engineer
Growth specialist — owns the path from "it works" to "it grows". Designs the North-Star + input-metric tree, instruments the activation/retention funnel (event schema), builds growth loops (referral / content / paid), and designs the experiments (A/B, holdout) that find product-market fit. Runs after the product is live (with/after performance-engineer), before hand-off to Maintainer. Writes docs/growth/GROWTH-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- prose-style
- Produces
- not declared
- Joins
- before devops
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/growth-engineer.md ↗
performance-engineer
Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is data-platform / enterprise / commerce.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- prose-style
- Produces
- not declared
- Joins
- before qa-engineer
suggested when files change: tests/k6/load.js · src/perf-budget.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/performance-engineer.md ↗
Maintainer (1)
infra-provisioner
Provisions the real backing infrastructure for a Product-Builder product so it reaches a live URL — managed Postgres (Neon default), the hosting project (Vercel default), env/secret wiring, and the custom domain + DNS + TLS. Pairs with devops (which does preview/staging only and refuses prod/real-domain). Runs after gate:ship is approved, before the production deploy. Plan-first and human-gated: it shows a provisioning plan with cost and waits for CTO approval before creating anything, is idempotent (re-running never duplicates resources), and records teardown. Writes docs/infra/PROVISION-{slug}.md.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- stack-baseline · cost-model · prose-style · done-blocked · observability-baseline
- Produces
- not declared
- Joins
- before devops via e2e-test-engineer
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/infra-provisioner.md ↗
Reviewers & Safety (39)
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/journal-entry.ts · lib/general-ledger.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/accounting-reviewer.md ↗
adtech-privacy-reviewer
US adtech / web-tracking privacy-litigation pre-implementation reviewer. Outputs threat model TM-adtech-{slug}.md and signs off the tracking-consent gate before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · skeptical-triage
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/adtech-privacy-reviewer.md ↗
ai-security-reviewer
AI-specific pre-implementation threat modelling for ai-system / agent-product archetypes. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: prompts/system.txt · src/rag/retriever.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/ai-security-reviewer.md ↗
api-platform-reviewer
API platform / dev-API pre-implementation reviewer. Outputs threat model TM-{slug}.md.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: api/openapi.yaml · src/webhooks.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/api-platform-reviewer.md ↗
cli-reviewer
CLI tool pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off CLI surface decisions before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: bin/great-cto · src/cli/main.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/cli-reviewer.md ↗
cmmc-reviewer
US defense-contractor (GovCon) pre-implementation reviewer. Outputs threat model TM-cmmc-{slug}.md and signs off the CMMC-assessment gate before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · skeptical-triage
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/cmmc-reviewer.md ↗
cms-reviewer
CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/cms-reviewer.md ↗
data-platform-reviewer
Data-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off retention + lineage decisions before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/data-platform-reviewer.md ↗
db-migration-reviewer
Database migration safety specialist. Activates when migrations/ files are detected in a PR or feature branch. Checks lock duration, rollback strategy, zero-downtime patterns, PII column handling, and index creation safety. Writes docs/migrations/MIGRATE-{slug}.md. Blocks deploy if no rollback path exists.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before qa-engineer
suggested when files change: db/migrations/0007_add_index.sql · prisma/migrations/20260801_init/migration.sql - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/db-migration-reviewer.md ↗
devtools-reviewer
Devtools (CLI plugin / IDE extension / dev SDK) pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off supply-chain decisions before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/devtools-reviewer.md ↗
dpdpa-reviewer
India DPDPA 2023 + IT Act + RBI specialist pre-implementation reviewer. Auto-invoked on `in` jurisdiction signal. Covers DPDPA consent obligations, Data Fiduciary duties, Data Principal rights, cross-border transfer restrictions, and RBI data localisation for fintech. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/dpdpa-reviewer.md ↗
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state student-privacy laws (SOPIPA-CA, NY 2-D). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/coppa-consent.ts · lib/student_data.py - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/edtech-reviewer.md ↗
enterprise-saas-reviewer
B2B / enterprise-SaaS pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off tenant-isolation decisions before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/scim/provision.ts · db/row-level-security.sql - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/enterprise-saas-reviewer.md ↗
firmware-reviewer
IoT/embedded specialist pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/firmware-reviewer.md ↗
game-reviewer
Game / interactive-entertainment pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off age-rating + COPPA decisions before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/loot_box.ts · config/esrb.json - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/game-reviewer.md ↗
gdpr-reviewer
GDPR + EU AI Act + NIS2 specialist pre-implementation reviewer. Auto-invoked when jurisdiction detection finds eu, uk, or br signals. Covers GDPR Art.5/6/9/25/32/35, DPIA, EU AI Act risk classification, and NIS2 Article 21 controls. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/gdpr-reviewer.md ↗
gov-reviewer
Government / public-sector specialist pre-implementation reviewer for gov-public archetype. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: config/fedramp-boundary.yaml · src/fisma-controls.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/gov-reviewer.md ↗
healthcare-reviewer
Healthcare-specific pre-implementation reviewer for archetype:healthcare. Specialises in HIPAA Security Rule (45 CFR 164.308–318), Business Associate Agreement (BAA) chain, FHIR/HL7 implementation gotchas, PHI access logging (immutable audit), HITECH breach-notification timelines, and HHS Office for Civil Rights (OCR) audit readiness. Outputs threat model TM-{slug}.md and signs off PHI-handling decisions before senior-dev starts.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked · discovery
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/hipaa-audit.ts · integrations/fhir/client.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/healthcare-reviewer.md ↗
hr-ai-reviewer
HR-AI / AI-recruiting pre-implementation reviewer. Outputs threat model TM-hrai-{slug}.md.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/hiring/rank.ts · lib/resume_screen.py - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/hr-ai-reviewer.md ↗
infra-reviewer
Infrastructure-as-code pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off destructive changes before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: infra/main.tf · helm/values.yaml - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/infra-reviewer.md ↗
insurance-reviewer
Insurance / InsurTech specialist pre-implementation reviewer for insurance archetype. Specialises in NAIC Model Acts (50-state filing matrix), the NAIC AI Model Bulletin 2023 (AIS Program, unfair-discrimination testing, DOI market-conduct readiness), Colorado SB 21-169 + NY DFS AI circular (insurance-specific algorithmic-discrimination testing), Solvency II (EU capital adequacy), IFRS 17 insurance contracts, ACORD standards, actuarial model auditability (ASOPs), anti-discrimination pricing analysis (disparate impact), claims fraud detection patterns, bordereau reporting for re-insurance. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/naic-filing.ts · lib/actuarial-model.py - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/insurance-reviewer.md ↗
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/iolta-ledger.ts · lib/conflict-check.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/legal-reviewer.md ↗
library-reviewer
Library / SDK pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off API stability decisions before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: Cargo.toml · pyproject.toml - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/library-reviewer.md ↗
marketplace-reviewer
Two-sided marketplace pre-implementation reviewer. SD), 1099-K reporting, escrow / hold-and-release, dispute mediation, two-sided fee model, EU DSA + P2B Regulation compliance. Outputs threat model TM-{slug}.md and signs off payout-flow + seller-onboarding decisions before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/marketplace-reviewer.md ↗
mcp-server-reviewer
MCP (Model Context Protocol) server pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off the tool surface before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: mcp-servers/llm-router/server.py · src/mcp.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/mcp-server-reviewer.md ↗
mlops-reviewer
MLOps / model lifecycle pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off training-pipeline + serving-strategy decisions before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/mlops-reviewer.md ↗
mobile-store-reviewer
Mobile-app pre-implementation reviewer for App Store / Play Store policy compliance. Outputs threat model TM-{slug}.md and signs off store-policy decisions before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: fastlane/Fastfile · ios/iap-manager.swift - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/mobile-store-reviewer.md ↗
msp-reviewer
Managed Service Provider (MSP) / IT-services specialist pre-implementation reviewer for enterprise-saas and devtools archetypes. Outputs threat model TM-msp-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/rmm-agent.ts · lib/credential-vault.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/msp-reviewer.md ↗
oracle-reviewer
Web3-DeFi specialist pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/oracle-reviewer.md ↗
pci-reviewer
Commerce-specific pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off scope decisions before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/billing/stripe-webhook.ts · api/refund.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/pci-reviewer.md ↗
procurement-reviewer
Purchasing / source-to-pay specialist pre-implementation reviewer for enterprise-saas and enterprise archetypes. Outputs threat model TM-procurement-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/purchase-order.ts · lib/punchout.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/procurement-reviewer.md ↗
rcm-reviewer
Healthcare Revenue Cycle Management (RCM) / medical-billing specialist pre-implementation reviewer for the healthcare archetype. Outputs threat model TM-rcm-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/cms-1500.ts · lib/prior-auth.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/rcm-reviewer.md ↗
regulated-reviewer
Regulated-industry specialist pre-implementation reviewer for fintech / regulated archetypes. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: config/dora-ict-register.yaml · src/nis2-controls.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/regulated-reviewer.md ↗
streaming-reviewer
Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/streaming-reviewer.md ↗
tax-reviewer
Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: src/form-8879.ts · lib/tax-prep.py - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/tax-reviewer.md ↗
us-ai-reviewer
US AI-governance pre-implementation reviewer — the US analogue of the EU AI Act coverage. Outputs threat model TM-usai-{slug}.md and signs off the AI-governance gate before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · skeptical-triage
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/us-ai-reviewer.md ↗
us-privacy-reviewer
US privacy law specialist pre-implementation reviewer. Covers CCPA/CPRA, US state privacy matrix (VA CDPA · TX TDPSA · FL FDBR · CO CPA · CT CTDPA), FTC Act § 5, COPPA (under-13), and GLBA (financial). Auto-invoked on us / us-ca jurisdiction signals. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/us-privacy-reviewer.md ↗
voice-ai-reviewer
Voice-AI / telephony pre-implementation reviewer. Specialises in TCPA prior-express-consent, STIR/SHAKEN attestation, state recording-consent matrix (one-/two-party), CRTC CASL (Canada), Ofcom CLI rules (UK), EU AI Act Article 50 synth-voice disclosure, deepfake laws (CA AB-2655, TN ELVIS Act), and PII redaction in transcripts/recordings. Outputs threat model TM-voice-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · prose-style
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: integrations/twilio-handler.ts · src/ivr/menu.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/voice-ai-reviewer.md ↗
web-store-reviewer
Pre-implementation Web Store policy reviewer for browser-extension archetype. Validates manifest.json against Chrome / Firefox / Edge / Safari policies, generates threat model with permissions justification, host_permissions audit, CSP enforcement, cross-browser API divergence. Outputs TM-{slug}.md and pre-flight checklist.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- archetype-review-base · receiving-code-review [external · superpowers] · prose-style · skeptical-triage · beads · done-blocked
- Produces
- not declared
- Joins
- before senior-dev
suggested when files change: extension/manifest.json · src/mv3-worker.ts - Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/web-store-reviewer.md ↗
Orchestration & Meta (4)
continuous-learner
Use at session end (auto-triggered by SessionEnd hook) or via /learn command. Extracts repeatable patterns, decisions, and cost outliers from the session and writes structured entries to .great_cto/lessons.md. Promotes high-confidence patterns to ~/.great_cto/decisions.md after ≥3 occurrences.
- Shell
- none
- Web
- yes
- Spawns agents
- no
- Skills
- beads
- Produces
- not declared
- Joins
- around the pipeline
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/continuous-learner.md ↗
coordinator
Multi-agent coordinator. Use when a CTO request spans 3+ independent work streams, requires parallel research before implementation, or the task graph is complex enough that sequencing matters. Orchestrates agents across the full DECOMPOSE→CLASSIFY→DISPATCH→MONITOR→SYNTHESIZE→VERIFY lifecycle.
- Shell
- full
- Web
- no
- Spawns agents
- yes
- Skills
- not declared
- Produces
- not declared
- Joins
- around the pipeline
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/coordinator.md ↗
knowledge-extractor
Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.
- Shell
- none
- Web
- no
- Spawns agents
- no
- Skills
- not declared
- Produces
- not declared
- Joins
- around the pipeline
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/knowledge-extractor.md ↗
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
- Shell
- full
- Web
- yes
- Spawns agents
- yes
- Skills
- beads · done-blocked · prose-style
- Produces
- audit
- Joins
- around the pipeline
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/project-auditor.md ↗
Role not assigned (1)
quant-researcher
Quantitative research agent for systematic-trading projects. Forms hypotheses, builds and runs backtests, and reports results with the validity conditions that make a backtest evidence rather than decoration — purged cross-validation with an embargo, stationarity, sample uniqueness under overlapping labels, transaction costs and slippage, and a trials count for multiple-testing. RESEARCH ONLY: it never places an order, never touches execution credentials, and never sizes a position. Outputs docs/research/QUANT-{slug}.md; a human decides what to do with it.
- Shell
- full
- Web
- yes
- Spawns agents
- no
- Skills
- quant-validation · prose-style · skeptical-triage · done-blocked · beads
- Produces
- not declared
- Joins
- around the pipeline
- Relevant for (applies_to)
- relevant — the orchestrator decides
- Source
- agents/quant-researcher.md ↗
Generated from great_cto v3.29.1.
Checks: 70 agents ok · pipeline map ok · file rules 28 ok
Files: agents/*.md · shared/pipeline.toml · shared/lifecycle-map.mjs · scripts/lib/approval-level.mjs · scripts/hooks/auto-attach-reviewers.mjs ↗ GitHub
Known gaps in the source: quant-researcher