audit

Plugin audit from marketplace quality-gates in AleksandarBisevac/claude-plugins. Commands read from the repo's manifest — 4 days ago.

Skills (2)

• audit-codebase

  Use when someone wants a whole codebase audited and fixed as tracked, resumable work — "audit this codebase", "find and fix everything wrong in this repo", "go through the app and clean it up", "set up an audit plan", "what audit phase is next" — rather than a one-shot look at the current diff. Rout

• audit-spend

  Use when someone asks what their Claude Code work has cost — "what did that cost", "how much have we spent", "where did the tokens go", "which model is burning the budget", "is the cache actually helping" — and wants it attributed to the work rather than a session total. Routes to /audit:usage.

Slash commands (21)

• /audit:bug

  Track bugs in the audit manifest — report (add), list, materialize a TDD fix task (fix), or close. Execution of the fix stays in /audit; the repro test must fail red-first, proving the bug.

• /audit:doctor

  Audit pipeline: diagnose the setup before it bites — interpreter the hooks will use, git root, config, manifest + shard integrity, which plan-gate tier is active, submodule conflicts, build runners, whether the skills the plan names would resolve from a clone or only here, whether hooks have ever fi

• /audit:guide

  Ask the plugin about itself — what a config key does, how the plan gate grades, what the journal can prove — answered from its own docs with a citation for every claim, by the read-only guide agent.

• /audit:init

  Multi-agent codebase audit that GENERATES the audit manifest (phases/tasks) at manifestPath. Interviews you for scope/goals, fans out parallel read-only explorers, synthesizes findings, then presents the proposed phases for approval BEFORE writing — approve to materialize, or park them as proposals

• /audit:layout

  Audit pipeline: choose how the manifest is stored — `sharded` (an index plus one file per phase: fewer tokens per phase run, parallel-safe across worktrees) or `single-file` (one file, one diff, no index). A layout CHOICE, not a version upgrade: both shapes are current, neither goes out of date, and

• /audit:logs

  Audit pipeline: prune the local feeds this plugin writes under logsDir — today the plan-gate events feed rendered by the panel Plan gate card. Removes rows that no longer belong (paths outside this repository, lines that are not JSON, optionally rows past an age you name), prints what went and what

• /audit:migrate

  Audit pipeline: LEGACY SPELLING of /audit:layout sharded — it still works and does exactly that. Kept so existing transcripts, runbooks and older docs resolve; new work should say /audit:layout <sharded|single-file>, which also goes back the other way.

• /audit:next

  Audit pipeline: execute the next ready task (phase order, then task-id order; a ready task fixing a suite red at base goes first), then report what is ready next. --dry-run previews without mutating.

• /audit:panel

  Audit pipeline: open / stop / check a local control-panel UI to visually manage .claude/audit.config.json and the manifest''s composition levers (reviewSkill, per-task skills/models, buildCommands) — with live validation and discovery of the skills & agents available in this repo + globally. Ephemer

• /audit:phase

  Audit pipeline: everything a phase has done to it — add one to a plan that already exists, run it end to end (every ready task, one at a time or as waves, then sign-off), pin which phase the pipeline reaches for first, or cancel one that will not be done. A bare `<phaseId>` runs it; --dry-run previe

• /audit:propose

  Manage parked phase proposals in the audit manifest — list them, materialize one (or all) into live phases, or drop one. Proposals are parked by /audit:init when the user declines (some of) the synthesized plan, and by /audit:phase add --park for a phase found on a phase branch; materialization is a

• /audit:report

  Audit pipeline: render a self-contained, interactive HTML + Markdown report (collapsible phases, filter/sort, optional AI summary, Save-as-PDF) — shareable as a CI artifact, or published to a link with --share. Read-only (never mutates the manifest).

• /audit:resume

  Audit pipeline: resume an interrupted run — find the in-progress phase and continue from the first uncommitted task.

• /audit:review

  Audit pipeline: re-run Phase sign-off for a phase on demand (e.g. after fixes) — review, test gate, invariant check, optional runtime boot, merge.

• /audit:run

  Audit pipeline: execute exactly one task by id, with status guards (done/blocked/in_progress) and blocker checks. --dry-run previews without mutating.

• /audit:status

  Audit pipeline: print manifest status — phases, tasks, bugs, the ready-now list and what each pending task is waiting on; or, with --gate, turn that same state into a CI pass/fail verdict over conditions you pick with --fail-on. Read-only, no locks, no mutations.

• /audit:sync

  Sync the audit manifest with Azure DevOps work items — set the connector up for the first time (connect: verify the transport, report which auth path is in effect, prove access read-only, detect the board''s process), push manifest bugs/tasks/phases to ADO (board states, sprint stamp, Remaining Work

• /audit:task

  Add a tracked task to the audit manifest — every answer is a flag, and the dialogue only covers what the caller did not pass — promote one to running, close one that landed, move one between phases, or cancel work that will not be done. `add` allocates the id, initializes all orchestrator fields, up

• /audit:usage

  Audit pipeline: token spend attributed by phase, task, model, author and time — with cache economics, cost-per-task and a usage trend. Read-only (never mutates the manifest).

• /audit:version

  Audit plugin version: which build is running, what the marketplace offers and whether it auto-updates, every installed copy, and the newest published release - each with where it was read - plus the exact commands to update. Read-only; one GitHub request unless --offline.

• /audit:worktree

  Audit pipeline: the worktrees this plan owns — list them with their merge state, add one for a phase so it can run in a parallel session, remove one, or sweep the ones whose work has already landed. The sweep is read-only until you name a verb; a worktree is only ever reaped when its branch is conta

Subagents (4)

• audit-executor

  Task executor for the audit orchestrator. Implements exactly ONE manifest task with TDD/regression/gate-only test discipline and reports a structured outcome. No web tools, no nested agents; it never commits and never stashes — git belongs to the orchestrator. Spawned by the audit plugin; not meant

• audit-explorer

  Read-only codebase auditor for /audit:init fan-out. Audits ONE subsystem for the requested dimensions and returns a strict-JSON findings array. Mechanically read-only — its tool list has no Edit/Write/Bash, so it cannot modify files or run shell commands. Spawned by the audit plugin; not meant for d

• audit-reviewer

  Reviewer for /audit. Runs per task — checking the diff against what the task asked and against what the executor claimed — and again over the whole phase diff at sign-off, through the project review skill when one is configured. Returns structured findings plus a separate intent answer. It cannot ed

• guide

  Answers questions about the audit plugin itself — what a config key does, how the plan gate grades, how the capability policy resolves, what the journal can and cannot prove — from the plugin''s own README, reference docs, schemas and SECURITY.md, with a citation for every claim. Mechanically read-o

Hooks (24)

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" guard-secrets-read.py ask

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" guard-history-rewrite.py ask

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" journal-writes.py open

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" guard-capabilities.py ask

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" guard-edits.py ask

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" require-plan.py ask

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" journal-writes.py open

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" guard-edits.py ask

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" require-plan.py ask

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" journal-writes.py open

• PostToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" require-plan.py open

• PostToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" remind-tdd.py open

• PostToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" guard-bash-writes.py open

• PostToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" journal-writes.py open

• PostToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" guard-bash-writes.py open

• PostToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" journal-writes.py open

• PostToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" require-plan.py open

• PostToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" journal-writes.py open

• UserPromptSubmit

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" detect-plan-skip.py open

• UserPromptSubmit

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" drive-without-model.py open

• SessionStart

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" meter-usage.py open

• Stop

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" meter-usage.py open

• SubagentStop

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" meter-usage.py open

• SessionEnd

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py-launch.sh" meter-usage.py open

Similar plugins