agent-layer

Explicit-only. Run a named autonomous mode, repeatedly selecting, implementing, and shipping coherent work while preserving anything blocked.

Use globally installed `playwright-cli` for browser automation, UI inspection, screenshots, Playwright test debugging, or test generation. Trigger when a task needs browser interaction or test repair. Do not use for generic tests, web search, non-browser docs, or API-only work.

Explicit-only. Align a feature specification, produce a reviewed plan, complete the local work, and ship the pull request.

Explicit-only. Review a plan/task/context artifact set and report material findings.

Explicit-only. Ship one pull request, observe hosted CI and review feedback, follow PR policy, reply to every eligible comment, and request merge authorization before merging and cleaning up.

Explicit-only. Verify completed work against its authoritative contract and report coverage, working-code evidence, material gaps, and the completion verdict.

Use Agent Dispatch MCP tools only when the user names an external dispatch target or another skill explicitly requires dispatch. Do not use it for generic subagent, second-agent, or fresh-context requests; use the built-in subagent instead.

Explicit-only. Evaluate feedback on an open pull request, implement accepted fixes, prepare replies, and return dispositions without committing, pushing, or posting.

Explicit-only. Implement supplied plan/task/context artifacts, review the changes, verify the contract, and repair material findings.

Explicit-only. Apply an explicit plan/task/context artifact set and report the resulting implementation and deviations.

Explicit-only. Produce and review an implementation-ready plan from a task source.

Explicit-only. Report-only review of a concrete file, directory, diff, range, working tree, or proactive hotspot for material correctness, risk, architecture, test, documentation, performance, reliability, and maintainability findings.

Use globally installed `ctx7` for API/library docs when local docs or CLI help are insufficient. Trigger for API syntax, config, setup, migrations, version-sensitive, or post-cutoff questions. Do not use for web research, local files, browser automation, or installs.

Explicit-only. Audit Markdown docs for static accuracy and cross-document consistency against the repo, fixing what is safe. Excludes memory files by default.

Explicit-only. Audit agent memory files (ISSUES, BACKLOG, ROADMAP, DECISIONS, COMMANDS, CONTEXT) for structure, staleness, placement, consistency, and DECISIONS.md bloat; fix accepted findings.

Explicit-only. Audit the existing test suite once for redundancy, misleading coverage, organization, and material behavioral gaps, directly fixing safe findings.

Explicit-only. Raise coverage to an explicit or repository-required target with coherent behavior-focused tests and authoritative coverage evidence. Do not use for full-suite cleanup or pruning tests added in the current diff.

Explicit-only. Run one cleanup and repair pass over uncommitted working-tree changes: prune test changes, simplify production changes, review the diff, and directly fix accepted findings.

Explicit-only. Reproduce an unexplained bug, prove its root cause, capture a failing test or diagnostic blocker, then make a proportional repair and verify it.

Explicit-only. Diagnose and directly repair failing checks on an open pull request, verify the repair locally, and return uncommitted changes and evidence to the caller.

Explicit-only. Run one wide, evidence-led quality sweep over a repository or named scope, repair material local and cross-cutting findings, review the concrete work, and verify the result.

Explicit-only. Audit product interfaces as component boundaries, score complexity, over-engineering, and debt, maintain .agent-layer/tmp interface-audit reports, and finish at the final recommendation gate. Use for fresh interface cleanup audits or --update refreshes; not for implementation.

Explicit-only. Run the repository's full documented check lane, directly repair observed failures, and repeat only until the lane passes or a concrete blocker remains.

Explicit-only. Map BACKLOG.md items into roadmap phases, checking issue and decision impacts and surfacing user-owned prioritization without making ambiguous roadmap edits. Do not use for implementation planning.

Explicit-only. Remove material internal complexity such as dead code, obsolete options, needless indirection, duplicate workflows, or misplaced boundaries while preserving external behavior.

Use Tavily CLI for web search, URL extraction, site mapping, and cited research. Trigger when the user needs current web info, asks to search/read a page, provides URLs, or wants a sourced report. Do not use for browser automation, local docs, or Tavily setup.

First command description.

Second command does something useful for testing wrap lines in codex skills.