memory-auditor-cowork

memory-auditor-cowork is a skill for Claude Code, Codex from KirKruglov/claude-skills-kit. It costs 112 tokens per session (2,697 once invoked), scanned A, original, MIT.

A review tool for Claude's file-based memory in Cowork, including saved preferences, project instructions, and automatic notes. Cowork is Claude's environment for working with files and tasks.

In plain words
What is it for?
Checking memory health, identifying entries to fix, and cleaning automatic memory files after confirmation.
Why use it?
It helps find conflicting, outdated, repeated, or unnecessary information that could make Claude respond incorrectly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Checking memory health, identifying entries to fix, and cleaning automatic memory files after confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kirkruglov/claude-skills-kit/memory-auditor-cowork
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add KirKruglov/claude-skills-kit --skill memory-auditor-cowork
Clone the repo
git clone --depth 1 https://github.com/KirKruglov/claude-skills-kit

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for memory-auditor-cowork

README.md
[![agentmods](https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/memory-auditor-cowork/github.svg)](https://agentmods.dev/skills/kirkruglov/claude-skills-kit/memory-auditor-cowork)
Your own site
<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/memory-auditor-cowork"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/memory-auditor-cowork/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for memory-auditor-cowork

Your own site · 80×15
<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/memory-auditor-cowork"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/memory-auditor-cowork.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.02697
Opus 5 $0.00056 $0.01349
Sonnet 5 $0.00022 $0.00539
Haiku 4.5 $0.00011 $0.00270

Measured 11d ago against content hash ab4f16aff4b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

memory-auditor-cowork scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/prompts-and-memory/memory-auditor-cowork/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: memory-auditor-cowork

Audit Claude's file-based memory in Cowork: detect problematic entries across auto-memory, CLAUDE.md, User Preferences, and Project Instructions. Propose specific fixes with user confirmation. Can automatically modify auto-memory files.


Triggers

Russian: "аудит памяти", "проверь память", "аудит", "почисти память", "разбери память", "что у меня в памяти", "ревью памяти" English: "audit memory", "memory audit", "check memory", "clean up memory", "review memory", "memory health check", "what's in my memory"


Language Detection

Determine the language of the user's first message. Use that language for all subsequent output. If the language is ambiguous, default to Russian.


Input

Explicit user command (trigger). Data for analysis comes from files and context available in the current Cowork environment.

Output

In-chat report following the fixed Output Template (see below). Layer overview, prioritized issue table, concrete actions: automatic for auto-memory, manual instructions for other layers.


Reference: Cowork Memory Layers and Access Rights

This reference defines the complete and closed list of layers. The skill works ONLY with these layers. Adding new layers, analyzing other sources (native Claude.ai memory, conversation_search, history) is prohibited.

Layer Description Location Skill access
auto-memory File-based memory: MEMORY.md (index) + individual .md files with frontmatter (name, description, type) .auto-memory/ directory — path determined from context or via search Read, edit, delete files via Read, Write, Edit. Update MEMORY.md
CLAUDE.md Global/project user instructions CLAUDE.md file in workspace root or .claude/ Read only. Provide manual instructions to user
User Preferences Personal user settings in system prompt Visible in conversation context (user_preferences block or equivalent) Read only. Provide manual instructions: Settings > Profile > Preferences
Project Instructions Project instructions set by user Visible in conversation context (project_instructions block or equivalent) Read only. Provide manual instructions to user

Read the full file on GitHub · 225 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 225 lines · 112 tokens per session scan A ab4f16aff4b0

Subscribe to this mod's changes

memory-auditor-cowork is a skill published in the GitHub repository KirKruglov/claude-skills-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 2,697 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

memory-management

Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.

w95/awesome-claude-corporate-skills · 54 tokens

ai-agents-architect

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.

sickn33/agentic-awesome-skills · 31 tokens

context-engineering

A project documentation framework that records a project's goals, requirements, roadmap, and current state in separate files. It also keeps those documents within set size limits for an AI coding agent.

hashgraph-online/awesome-codex-plugins · 73 tokens

ask

Adaptive vault reader skill. Receives a natural language question, searches the vault first (Glob/Grep, entity reads, wikilink traversal), then self-assesses whether more context is needed. Escalates to /graphify for graph-level understanding or to /bedrock:teach for remote content ingestion only when the vault alone…

ccplugins/awesome-claude-code-plugins · 141 tokens

compress

Vault alignment engine. Detects and fixes 5 types of structural misalignments: broken backlinks, concept fragmentation, entity miscategorization, duplicated entities, and misnamed entities. Delegates all writes to /bedrock:preserve. Supports interactive mode (user confirmation) and cron mode (autonomous mechanical…

ccplugins/awesome-claude-code-plugins · 104 tokens

waggle-recall

Recall project-scoped Waggle history about a topic, component, decision, bug, experiment, or implementation attempt.

hashgraph-online/awesome-codex-plugins · 28 tokens