Audits a repository and prepares it for AI-first work with agents. It adds skills for drafting architecture decision records, mapping modules, writing repo conventions, setting up Codex CLI sandbox configs, and checking that declared build and test commands run.
@filip-podstavecUSE WHEN a load-bearing architectural decision is being made in conversation (database / framework / auth model / integration…
@filip-podstavecUSE WHEN setting up a repo for AI-first work, after a major directory restructure, or when an agent needs structured answers like…
@filip-podstavecUSE WHEN setting up Codex CLI in a project, tightening sandbox for prod/CI, or when user asks about Codex permissions.…
@filip-podstavecUSE WHEN setting up a repo for AI-first work (after /init-repo), or when the context-surface hook should start feeding repo…
@filip-podstavecUSE WHEN the user explicitly asks to verify that this repo's DECLARED build/test/lint commands actually run ("does the quickstart…
@filip-podstavecUSE WHEN about to open a PR, when teammate asks "what's in this diff?", or when returning to a branch and needing…
@filip-podstavecUSE WHEN setting up a repo for AI-first work, when an agent hallucinates domain term meaning, or when user asks to bootstrap /…
@filip-podstavecUSE WHEN starting work in a project that lacks a claude-leverage AGENTS.md (no `claude-leverage:` marker blocks at git root), or…
@filip-podstavecUSE WHEN auditing logging in a legacy codebase, after adopting the JSON-lines spec, or when user asks to clean up logging. Finds…
@filip-podstavecUSE WHEN documenting a non-obvious workflow prose explains poorly, or when user describes a multi-step process and asks for a…
@filip-podstavecUSE WHEN AIDEV anchors / per-dir AGENTS.md / ADRs have changed in this repo and the smart-context-surfacing PreToolUse hook needs…
@filip-podstavecUSE WHEN inheriting a legacy repo, when user asks "what's missing for AI-first work here?", "is this repo agent-ready?", "audit…
@filip-podstavecCode review on Sonnet — security/correctness/maintainability findings, read-only. Use before commits or PRs.
@filip-podstavecPre-fetch implementation context (key files, types, patterns) on Haiku, read-only. Use before multi-file features.
@filip-podstavecUse when the user wants documentation checked for freshness after code changes. Reads diff and existing docs, proposes specific…
@filip-podstavecUSE WHEN a test intermittently fails on unchanged code. Runs it N times sequentially, captures pass/fail + stderr, groups…
@filip-podstavecReview pre-extracted code snippets passed in the prompt — never re-reads files, never runs git diff. Hard 500-token output cap.…
@filip-podstavecStage/commit/push non-trivial changes on Sonnet using Conventional Commits. Reads diff, matches repo style.
@filip-podstavecTrivial commits on Haiku — 1 file, <20 lines, no sensitive paths. Speed-optimized, separate rate pool.
@filip-podstavecFind all call sites of a symbol with structured output on Haiku — for 'what breaks if I change X?' questions. Returns…
@filip-podstavecRun a shell command and return structured digest of its output on Haiku — for commands that produce >2k tokens of output (pip…
@filip-podstavecUSE WHEN /repo-doctor --semantic runs. Judges whether discoverability artifacts (AGENTS.md, README, ADRs, GLOSSARY, per-dir…
@filip-podstavecUse for codebase discovery. Use to find where something is defined or imported. Use to identify patterns used across files. Use…
@filip-podstavecUse to understand how something works in the codebase before making changes. Use when asked to explain a pattern or flow that…
@filip-podstavecDelegate code review to the code-reviewer subagent (Sonnet, read-only) and apply approved fixes in the main session
@filip-podstavecCheck documentation freshness after code changes. Delegates to docs-updater subagent (Sonnet) to propose doc/changelog updates -…
@filip-podstavecDiagnose a flaky test by running it N times. Delegates to flaky-test-isolator subagent — N runs, signature-grouped failures,…
@filip-podstavecGather implementation context before starting a task. Delegates to context-gatherer subagent (Sonnet) to pre-fetch everything…
@filip-podstavecDelegate test execution to the test-runner subagent (Sonnet) and apply approved fixes in the main session
@filip-podstavecIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
