Agent
Stress-tests a REQ's architecture and task plan before the human reviews them. Assumes the design is wrong, broken, or incomplete, tries to prove it, and reports only the findings that survive its own refutation attempts. Hunts what was omitted entirely, not just flaws in what was written. Read-only — reports…
Agent
Reviews code changes for layering compliance, separation of concerns, API contracts, and integration with existing patterns. Read-only — reports findings without modifying code. Dispatched by /review during Phase 4.
Agent
Explores the codebase for a given REQ: finds similar existing code, the files the change will touch (blast radius), where the new code hooks in, and what tests exist. Read-only. Dispatched by /architect and /bugfix.
Agent
Reviews code changes for logic errors, race conditions, error handling gaps, and security vulnerabilities. Read-only — reports findings without modifying code. Dispatched by /review during Phase 4.
Agent
Decides a single pipeline gate during an autonomous run — /autopilot, or /sprint adjudicating its gate queue (autonomy.gates set to assisted or auto). Reads the gate's evidence packet and returns one verdict — APPROVE, REWORK, or HALT — with a confidence score and cited evidence. Read-only on source; writes only its…
Agent
Audits the UI source for design-system problems without running the app — hardcoded values that should be tokens, too many font sizes or spacing values, duplicated components, inconsistent names, screens that disagree with each other, and code that breaks the documented design system (with the cause classified). When…
Agent
Standalone codebase health audit — tech debt, code smells, dead code, complexity hotspots, missing tests. Operates on the whole codebase, not a single REQ. Read-only. Dispatched by /analyze.
Agent
Standalone performance and cost audit — API cost hotspots, database performance issues (N+1, missing indexes, full scans), latency drivers (sync I/O, unbounded loops, blocking calls). Read-only. Dispatched by /optimize.
Agent
Runs the complete /proceed pipeline for a single REQ inside an isolated worktree. All phases sequential within this agent's own context — CANNOT dispatch sub-agents. Pauses at every gate; surfaces gate-claims to the /sprint orchestrator. Dispatched only by /sprint.
Agent
Reviews code changes for convention compliance, naming, duplication, and test coverage. Read-only — reports findings without modifying code. Dispatched by /review during Phase 4.
Agent
Self-review against the captured knowledge vault. Checks whether the new code repeats any known mistake (lessons), respects any codebase quirk (gotchas), and conflicts with any accepted decision (ADRs), and sweeps user-facing repo docs for staleness against the change. Read-only — reports findings. Dispatched by…
Agent
Implements a single task end-to-end — writes code, updates tests, verifies it runs. Reads the task spec, the surrounding code, and the vault. Drafts a commit message; does NOT commit. Dispatched by /implement.
Agent
Runtime UI/UX review of a change. Starts the app's dev server and drives a browser to confirm the changed UI renders, the flows work, the interaction states are correct (disabled/loading/error/empty, not just the happy view), and the result matches the design and UI acceptance criteria — the things static review…
Skill Claude CodeCodex
Standalone codebase health audit. Dispatches the health-auditor agent and produces a dated report in .adlc/audits/. No pipeline state, no gates — read-only audit that you run periodically or on demand.
Skill Claude CodeCodex
Design the architecture and task breakdown for a REQ. Phase 2 of /proceed. Dispatches codebase-explorer to inform the design, then drafts architecture.md and tasks/TASK-.md. On high-stakes REQs, dispatches the architecture-adversary to attack the design before the gate so the user reviews a stress-tested plan. Ends in…
Skill Claude CodeCodex
Autonomous end-to-end pipeline. Runs /spec → /architect → /implement → /review → /wrapup like /proceed, but instead of pausing at each gate it routes the decision through the decision-maker agent, commits its work as it goes, and ends in a single final human review backed by a full audit log. Opt-in; conservative by…
Skill Claude CodeCodex
Streamlined pipeline for bug fixes. Slimmer than /proceed — bug report → investigate → fix → verify → ship, with gates between each. Use for defects, not for new features. Larger or scope-creeping bugs should be re-framed as a REQ via /spec.
Skill Claude CodeCodex
View and change ADLC project settings in .adlc/config.yml — git policy, isolation, how freely the assistant may edit, external sources, autonomy levels, stack, protected branches, repos — through guided options, then re-sync any derived files. Also migrates an existing vault's config to pick up new keys after a…
Skill Claude CodeCodex
Execute the task DAG for a REQ. Phase 3 of /proceed. Dispatches task-implementer agents (tier-based parallel where possible), drafts commit messages to commits-draft.md, runs tests, then ends in the implement gate.
Skill Claude CodeCodex
Bootstrap the .adlc/ vault in a new repo — copies templates, generates the CLAUDE.md schema doc, creates empty vault files (now, hot, index, decisions, glossary, gotchas), and scans for existing documentation (README, ARCHITECTURE, CONTRIBUTING, lint configs, prior ADRs, GLOSSARY) to seed context/ and architecture/…
Skill Claude CodeCodex
Standalone performance and cost audit. Dispatches the performance-scanner agent and produces a dated report in .adlc/audits/. Identifies LLM/API cost hotspots, DB performance issues, latency drivers, caching opportunities. No gates — read-only.
Skill Claude CodeCodex
End-to-end pipeline orchestrator. Runs /spec → /architect → /implement → /review → /wrapup in sequence with gate-pause between every phase. Resumable from any phase via pipeline-state.json. Use this when you want the full pipeline rather than invoking each phase skill separately.
Skill Claude CodeCodex
Reconcile pipeline-state.json against git reality for one, several, or all in-flight REQs and bugs. Diagnoses each as in-sync, stale-state, abandoned, sprint-stuck, or divergent, then surfaces a triage queue and back-fills the vault for REQs whose code shipped without /wrapup running. Read-only on code and git…
Skill Claude CodeCodex
Multi-perspective code review for a REQ. Phase 4 of /proceed. Dispatches 4 read-only review agents in parallel (correctness, quality, architecture, reflector) — plus a 5th ui-reviewer that runs the app in a browser when the change touches a UI surface — consolidates findings by severity, and ends in the verify gate.