Registry

Go phase. Reads the approved SPEC file, maps Requirements to tasks (plan), executes via TDD (build), and integrates results verifying all Acceptance Criteria.

Test-Driven Development enforcer. Red→Green→Refactor cycle with no production code without a failing test first. Use for new features and bug fixes.

Quality and performance evaluation with baseline comparison. Sub-modes: correctness, performance, quality, regression. Outputs PASS/WARN/FAIL per dimension. Use for pre-ship evaluation or regression checks.

Conventional Commits 1.0 generator. Stages relevant files, infers type(scope): description, never uses --no-verify.

Performance optimizer for loops, DB queries, rendering, and batch operations. Catches N+1 queries, missing indexes, and unnecessary re-renders.

Context window manager. Snapshots session state, compacts conversation, and resumes via hook. Use when context exceeds 70% or a large new task begins.

Use when all plan tasks are done and green to review, archive planning artifacts, and ask how to finish.

Trigger: vague/unfocused request or solution-without-problem. Also invoked via /discover command. Reframes goal before acting.

Spec phase. Converts user requirements into a numbered Requirements + Acceptance Criteria document saved as SPEC-{timestamp}.md. Prompts /team suggestion when 3+ requirements are detected.

Org-level agent team designer via `epic team` CLI (cross-project, append-merge). Subcommands: list, show, sync, link, unlink, history. Use when setting up agents, designing teams, or /spec yields 3+ requirements.

Audit Archcore docs: dashboard (counts, status, relations, orphans), deep coverage audit, or drift detection (code/cascade/temporal staleness). Use for 'show status', 'documentation gaps', 'check if docs match code', or after a staleness warning. Not for creating docs.

Check phase. Launches parallel review (code quality + security + tests) with scope-based extras (API contract, accessibility, migration safety). Outputs PASS/WARN/FAIL per dimension with spec coverage verification.

Use for bugs, unexpected behavior, regressions, or failing tests you did not write.

State-persisted autonomous pipeline: spec → go → audit → eval → ship → evolve in one command. Auto-detects direct/council/interactive mode. Crash-recoverable via PIPELINE-*.json. Hands-off until PR.

Ring 3 evolution engine. Analyzes session observations, generates and improves evolved skills, shows metrics dashboard. Subcommands: status, history, rollback, reset. Use for post-session review and skill improvement.

Security review checklist with optional engagement scoping. Use when auth, DB, API, infra, or secrets code is touched.

Adversarial validation of vulnerability findings. Use when triaging security findings, validating vulnerabilities, or prioritizing remediation.

Pre-merge verification gate. Build, test, and lint must all pass before marking done or shipping.

HarnessX Critic (Tier 2.1) — adversarial review of evolved-skill proposals against trace evidence. Detects reward hacking and manifest/evidence contradictions. Out-of-band LLM counterpart to the in-loop deterministic critic in src/evolve/critic.rs.

4-voice parallel deliberation (Architect · Skeptic · Pragmatist · Critic) for architecture, tech selection, or design decisions with no clear answer. Anti-anchoring: each voice gets independent context. Records decision in harness-mem.

On-demand human self-assessment of AI usage quality. Scores 5 dimensions from session data. Not agent performance review.

HTTP API-based documentation server (always running). Questions about project architecture, conventions, decisions, code structure, tech debt, env config, progress, or doc health. Also: init project, audit docs, lint, validate, promote note, rebuild index, search vaults.

Documentation generator for public APIs, functions, and modules. Use when exports, signatures, or new modules are added or changed.

Code simplification for high-complexity files. Targets deep nesting, copy-paste patterns, god functions, and files over 200 lines.

Core router. Always active. Auto-invokes matching skill before every response. Runs confusion protocol on high-risk ambiguity.

Systematic vulnerability scanner across injection, auth, data exposure, and dependencies. Use when scanning for vulnerabilities, reviewing security, or validating threat models.

Trigger: active multi-agent run. Handles inbox reading, dep resolution, message formatting, handoffs. Also provides status dashboard and intervention control via internal modes.

Threat modeling and attack surface analysis. Use when assessing security boundaries, modeling threat actors, or generating threat scenarios.

Loop-breaking self-diagnosis. Use when 3+ consecutive failures occur, circular retries persist, or context overwhelms the session.