How do I install the Audit skill?

Run npx skillmds@latest add openwpm/audit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Audit safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Audit?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Audit free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

openwpm (@openwpm) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Audit by openwpm — Agent Skill

Name: Audit
Author: openwpm

Audit

Use when stuck, confused, or disoriented in a crosslink-tracked project — dumps the full context (session state, active issue, locks, blockers, hook config, git state, project rules) so you can re-orient and decide a next action. Trigger when the user says "I'm stuck", "audit", "what's going on", or asks for a context dump.

openwpm 1f0c3b3 2.6 KB Updated Sep 17, 2026

File contents

Audit — full context dump for re-orientation

Use this when you (or the user) have lost the plot in a crosslink-tracked project. The skill walks through every state surface and prints results so the next decision is grounded in real data, not guesses.

1. Project grounding (same as preflight)

Read core rules:

Read .crosslink/rules/global.md

Detect languages and read relevant rule files (check for Cargo.toml, package.json, tsconfig.json, pyproject.toml, go.mod, etc.).

Read project-specific rules:

Read .crosslink/rules/project.md

Read tracking rules based on current mode:

crosslink config get tracking_mode

Then read .crosslink/rules/tracking-<mode>.md.

2. Project tree scan

ls -1

Scan the project tree (max depth 3, max 50 entries) to ground yourself on actual paths.

3. Dependency versions

Read the primary manifest file to confirm actual dependency versions.

4. Session state

crosslink session status

What issue is being worked on? What was the last action?

5. Active issue details

If working on an issue, get full details:

crosslink issue show <issue-id>

Review all comments, especially plan and decision comments.

6. Related issues and blockers

crosslink issue blocked
crosslink issue ready

Are there blocking dependencies? What's unblocked and available?

7. Lock state

crosslink locks list 2>/dev/null

Are any issues locked by other agents?

8. Recent interventions

Check if there have been recent hook blocks or driver redirects by reviewing recent issue comments.

9. Hook configuration

crosslink config show

What tracking mode is active? What commands are blocked/gated?

10. VCS state

jj status
jj log -r '..@' --limit 5
jj diff --stat

What's the current change state? Any uncommitted working-copy changes?

11. Print diagnostic summary

Audit summary:
  Session:    active / working on #<id>
  Change:     <current change / bookmark>
  Tracking:   <mode>
  Languages:  <list>
  Open issues: <count>
  Blocked:    <count>
  Locks:      <count>
  Uncommitted: <count> files changed

Loaded rules: global.md, <lang>.md, tracking-<mode>.md, project.md

You are now fully re-oriented. Decide your next action based on this context.

---name: auditdescription: Use when stuck, confused, or disoriented in a crosslink-tracked project — dumps the full context (session state, active issue, locks, blockers, hook config, git state, project rules) so you can re-orient and decide a next action. Trigger when the user says "I'm stuck", "audit", "what's going on", or asks for a context dump.---# Audit — full context dump for re-orientationUse this when you (or the user) have lost the plot in a crosslink-tracked project. The skill walks through every state surface and prints results so the next decision is grounded in real data, not guesses.## 1. Project grounding (same as preflight)Read core rules:```Read .crosslink/rules/global.md```Detect languages and read relevant rule files (check for `Cargo.toml`, `package.json`, `tsconfig.json`, `pyproject.toml`, `go.mod`, etc.).Read project-specific rules:```Read .crosslink/rules/project.md```Read tracking rules based on current mode:```bashcrosslink config get tracking_mode```Then read `.crosslink/rules/tracking-<mode>.md`.## 2. Project tree scan```bashls -1```Scan the project tree (max depth 3, max 50 entries) to ground yourself on actual paths.## 3. Dependency versionsRead the primary manifest file to confirm actual dependency versions.## 4. Session state```bashcrosslink session status```What issue is being worked on? What was the last action?## 5. Active issue detailsIf working on an issue, get full details:```bashcrosslink issue show <issue-id>```Review all comments, especially plan and decision comments.## 6. Related issues and blockers```bashcrosslink issue blockedcrosslink issue ready```Are there blocking dependencies? What's unblocked and available?## 7. Lock state```bashcrosslink locks list 2>/dev/null```Are any issues locked by other agents?## 8. Recent interventionsCheck if there have been recent hook blocks or driver redirects by reviewing recent issue comments.## 9. Hook configuration```bashcrosslink config show```What tracking mode is active? What commands are blocked/gated?## 10. VCS state```bashjj statusjj log -r '..@' --limit 5jj diff --stat```What's the current change state? Any uncommitted working-copy changes?## 11. Print diagnostic summary```Audit summary: Session: active / working on #<id> Change: <current change / bookmark> Tracking: <mode> Languages: <list> Open issues: <count> Blocked: <count> Locks: <count> Uncommitted: <count> files changedLoaded rules: global.md, <lang>.md, tracking-<mode>.md, project.md```You are now fully re-oriented. Decide your next action based on this context.

Frequently asked questions