Fleet Feature Catalog
Auto-generated by
scripts/gen-features.mjsfrom the bundled skill/crew/role/workflow frontmatter. Do not edit by hand — runnpm run build(ornode scripts/gen-features.mjs) to regenerate.
A compact index of fleet capabilities shipped with this release. For full documentation see the other files in this docs/ directory.
Totals: 16 workflows · 9 skills · 41 roles · 5 crews (71 features)
Workflows
| Name | Invocation | Description |
|---|---|---|
adversarial-research | /research <topic or question> | Adversarial deep research on a topic (parallel explorers + critic) |
approval-gate | — | Demo — build → human approval interrupt → deploy. Bundled example for #369 Phase 3C interrupts. |
brainstorm | — | Pre-feature brainstorming workflow. Spawns 3 parallel adversarial inquisitor agents (UX, technical, edge-cases) in round 1 to grill the user with questions until consensus is reached. Standalone (/brainstorm) writes 00-brainstorming.{md,context.md} in its own slug dir; chained via /feature --deep-brainstorm writes 01-brainstorming.md inline in the feature slug. |
bug-autopilot | /bug-autopilot <bug description or repro> [--scope diff|full] [--legacy-workflow-dispatch] | End-to-end bug-fix autopilot: reproduce → fix → regression-test → code-review loop → open PR → wait for human approval → iterate on feedback → merge. |
code-review | /code-review [path or git-range] | Run comprehensive multi-agent code review |
code-review-autopilot | /code-review-autopilot [target] [--scope=diff|full] [--ship] [--max-stage-visits <N>] [--legacy-workflow-dispatch] | Iterative code-review auto-pilot: review → triage → fix → validate, looping until convergence; optional PR handoff via --ship. Pass --scope=full to audit the whole codebase instead of a diff. |
compose-review | — | Cross-feature composition demo — fan-out per-file reviews → user approval interrupt → conditional apply/skip → report (#369 Phase 3A + 3B + 3C) |
feature-pipeline | — | 7-phase feature planning pipeline (brainstorm → requirements → research → design → validation → DoD → tasks) — drives the /feature slash command |
fixer-loop | /fixer-loop [--max-iterations <N>] [--plan-dir <path>] [--legacy-workflow-dispatch] | Auto-pilot loop that reviews, triages, fixes, and verifies. Iterates until convergence or budget exhausted. |
freeform | — | No-op workflow for ad-hoc/freeform crew operation |
github-issue-worker-autopilot | /github-issue-worker-autopilot [--max-stage-visits <N>] [--legacy-workflow-dispatch] | GitHub-issues-driven autopilot: triage open issues, fix, validate with tests, generate proof artifacts, and ship as a draft PR. |
init-investigation | /init [refresh] [--legacy-workflow-dispatch] | Workflow-driven /init — parallel investigators + critic + synthesizer |
per-file-review | — | Demo — fan-out per-file reviews and gather into a single digest (#369 Phase 3B) |
planning | — | Multi-step planning workflow with adversarial research, DoD, task breakdown, and execution |
subgraph-example | — | Demo — parent workflow that invokes code-review as a subgraph stage |
triage | — | Investigate then branch — fix / review / skip — based on artifacts, placeholders, and ifResult |
Skills
| Name | Invocation | Description |
|---|---|---|
agents-fleet-conventions | — | Shared conventions for agents-fleet codebase (TypeScript/ESM/branded types/named exports) |
coordinator-worker-architecture | — | agents-fleet coordinator-worker primitives, boundaries, and concurrency |
hub-tool-discipline | — | Hub topology — workers MUST route ALL coordinator-bound communication through report_to_coordinator |
ponytail-minimalism | — | YAGNI ladder and minimalism rules — forces the laziest solution that actually works |
ponytail-review | — | Over-engineering code review — finds what to delete, replace with stdlib/native, or shrink |
prepared-statements-pattern | — | IntelDatabase prepared-statement conventions for better-sqlite3 (WAL, sync, idempotent migrations) |
react-ink-patterns | — | React 18 + Ink 5 terminal-UI patterns — function components, hooks, Static, Box layout, polling |
security-audit-checklist | — | Threat-model audit checklist — path traversal, SQL injection, prototype pollution, credentials, command injection, MCP allowlists |
vitest-patterns | — | Vitest 4.x test patterns — fixtures, mocking, async, tmpDir cleanup |
Roles
| Name | Type | Description |
|---|---|---|
architecture-reviewer | agent_type: reviewer | Architecture and design pattern reviewer |
context-researcher | agent_type: explorer | Context and dependencies researcher - investigates surrounding context and historical background |
correctness-reviewer | agent_type: reviewer | Logic and correctness focused code reviewer |
counter-researcher | agent_type: explorer | Counter-arguments and alternatives researcher - investigates downsides and alternative approaches |
default-coder | agent_type: coder | Default system prompt for coder worker agents |
default-coordinator | agent_type: coordinator | Default coordinator system prompt for fleet orchestration |
default-explorer | agent_type: explorer | Default system prompt for explorer worker agents |
default-general-purpose | agent_type: general-purpose | Default system prompt for general-purpose worker agents |
default-researcher | agent_type: researcher | Default system prompt for researcher worker agents |
default-reviewer | agent_type: reviewer | Default system prompt for reviewer worker agents |
default-tester | agent_type: tester | Default system prompt for tester worker agents |
edge-case-researcher | agent_type: explorer | Edge cases and failure modes researcher - investigates what could go wrong |
fleet-architect | agent_type: reviewer | Architecture reviewer specialized for agents-fleet coordinator-worker patterns |
fleet-coder | agent_type: coder | Coder agent specialized for agents-fleet (TypeScript/ESM/Ink/Copilot SDK) |
fleet-correctness-reviewer | agent_type: reviewer | Correctness reviewer specialized for agents-fleet type safety and async patterns |
fleet-explorer | agent_type: explorer | Read-only explorer specialized for investigating the agents-fleet codebase |
fleet-maintainability-reviewer | agent_type: reviewer | Maintainability reviewer specialized for agents-fleet code hygiene and conventions |
fleet-minimalism-reviewer | agent_type: reviewer | Minimalism / over-engineering reviewer — finds what to delete, replace with stdlib/native, or shrink |
fleet-performance-reviewer | agent_type: reviewer | Performance reviewer specialized for agents-fleet runtime efficiency and resource usage |
fleet-researcher | agent_type: researcher | Research and investigation agent with scoped write access for the agents-fleet codebase |
fleet-security-reviewer | agent_type: reviewer | Security reviewer specialized for agents-fleet threat model |
fleet-tester | agent_type: tester | Tester agent specialized for agents-fleet (Vitest/better-sqlite3/real implementations) |
init-api-explorer | agent_type: coder | Investigates API surface and contracts |
init-arch-explorer | agent_type: coder | Investigates architecture and project structure |
init-build-explorer | agent_type: coder | Investigates build system, test framework, and dev workflow |
init-critic | agent_type: reviewer | Adversarial critic that verifies investigation findings |
init-decision-explorer | agent_type: coder | Investigates key design decisions and rationale |
init-dep-explorer | agent_type: coder | Investigates dependencies and external services |
init-pattern-explorer | agent_type: coder | Investigates coding patterns and conventions |
init-security-explorer | agent_type: coder | Investigates security model and authentication |
inquisitor-edge-cases | agent_type: explorer | Adversarial edge-cases-angle inquisitor that grills the user with questions about failure modes, security, malformed input, and adversarial scenarios before a feature is built. Spawned by /brainstorm in round 1 alongside inquisitor-ux and inquisitor-technical. |
inquisitor-technical | agent_type: explorer | Adversarial technical/integration-angle inquisitor that grills the user with questions about architecture, integration points, data shapes, and operational concerns before a feature is built. Spawned by /brainstorm in round 1 alongside inquisitor-ux and inquisitor-edge-cases. |
inquisitor-ux | agent_type: explorer | Adversarial UX-angle inquisitor that grills the user with questions about intent, workflows, success criteria, and user experience before a feature is built. Spawned by /brainstorm in round 1 alongside inquisitor-technical and inquisitor-edge-cases. |
performance-reviewer | agent_type: reviewer | Performance and efficiency focused reviewer |
planning-coordinator | agent_type: coordinator | Coordinator specialized for planning workflows - brainstorming, requirements, and design |
ponytail-coder | agent_type: coder | Minimalist coder — a lazy senior developer who writes the least code that works |
primary-researcher | agent_type: explorer | Primary research perspective - direct investigation of facts, code, documentation, examples |
research-coordinator | agent_type: coordinator | Coordinator specialized for parallel research and investigation workflows |
research-critic | agent_type: reviewer | Adversarial critic that cross-references and verifies research findings |
security-reviewer | agent_type: reviewer | OWASP-focused security audit reviewer |
test-reviewer | agent_type: reviewer | Test coverage and quality reviewer for agents-fleet (TypeScript/Vitest) |
Crews
| Name | Workflow | Description |
|---|---|---|
agents-fleet-crew | /planning | Default development crew for agents-fleet |
code-review-crew | /code-review | Multi-perspective code review crew (4 reviewers + synthesis) |
init-crew | /init-investigation | Codebase investigation crew for /init command |
minimal-dev-crew | — | Minimalist dev crew — ponytail coder implements, reviewer audits for over-engineering |
research-crew | /adversarial-research | Adversarial research crew — 4 angles + critic |