Claude skill
Audit Memory
Audit Memory is a Claude skill in the Deckhand plugin. Audit this repo's agent rules and memory files (CLAUDE.md, AGENTS.md, Cursor rules, the agent's memory folder) for lines that are wrong, out of date, in conflict, or no longer followed by the code.
What it does
The description in the skill's SKILL.md, which Claude reads to decide when to use it:
Audit this repo's agent rules and memory files (CLAUDE.md, AGENTS.md, Cursor rules, the agent's memory folder) for lines that are wrong, out of date, in conflict, or no longer followed by the code. Use when the user asks to audit, check or clean up CLAUDE.md, AGENTS.md, rules or memory files, or asks why the agent keeps getting a rule wrong.
The skill's instructions (about 982 words) cover:
- 1. Collect the files
- 2. Split each file into claims
- 3. Check each claim against the repo
- 4. Check against Harbor, when it is connected
- 5. Report
How to use it
- Audit Memory comes inside the Deckhand plugin, so you get it by installing that plugin, along with its 6 other skills. A plugin installs as one unit, with all its skills. The plugin's page has the install steps, and plugins are saved to your Claude account.
- Ask Claude for the task. When your request matches the skill's description, Claude loads it.
- To pick it yourself in Claude chat, type
/or click + and choose audit-memory. In Claude Code and Cowork, type:/deckhand:audit-memory
Source
- Plugin
- Deckhand
- SKILL.md
- View on GitHub
- Repo stars
- 3
- Repo last pushed
- Nov 13, 2026
- Checked
- Nov 16, 2026
More skills in Deckhand
- Check DiffCheck the current changes against this repo's own agent rules (CLAUDE.md, AGENTS.md, Cursor rules, Copilot instructions) before committing.
- Context CostMeasure how many tokens your coding agent reads before you type anything (CLAUDE.md and AGENTS.md chains, imports, memory files, always-on Cursor rules, skills and MCP servers), find what is stale…
- Rules From ReviewsRead this repo's recent merged pull request reviews on GitHub, find what reviewers keep asking for, and draft those asks as agent rules (for AGENTS.md, CLAUDE.md or Cursor rules) when the rules…
- Rules ScoreScore this repo's agent rules files (CLAUDE.md, AGENTS.md, Cursor rules, Copilot instructions) from 0 to 100 on a fixed rubric (accurate, covers the essentials, specific, lean, no noise), show what…
- Told You TwiceRead your own past coding agent sessions (Claude Code and Codex logs on this machine), find the corrections you gave the agent more than once ("no, use pnpm", "stop adding comments", "I told…
- Write RulesWrite this repo's agent rules file (AGENTS.md, read by Claude Code, Codex, Cursor and others) from what the repo actually does (CI workflows, scripts, configs, folder layout, git history), with a…