audit-agent-memory

audit-agent-memory is a skill for Claude Code from cpliakas/claude-code-engineering-leaders. It costs 81 tokens per session (2,349 once invoked), scanned A, original, MIT.

A check of one coding agent’s project memory folder for organization and maintenance problems, such as dead links, overly large files, or content that should not be stored there.

In plain words
What is it for?
Use it to inspect an agent’s memory after setup or when its stored project knowledge seems confusing, oversized, or stale.
Why use it?
It helps find memory that is outdated, bloated, or difficult for the agent to use. The check produces advice but does not change files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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.

agentmods
npx agentmods add skills/cpliakas/claude-code-engineering-leaders/audit-agent-memory
Any agent
npx skills add cpliakas/claude-code-engineering-leaders --skill audit-agent-memory
Clone the repo
git clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leaders

Made for: Claude Code.

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 audit-agent-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/audit-agent-memory.svg)](https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/audit-agent-memory)
Your own site
<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/audit-agent-memory"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/audit-agent-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00081 $0.02349
Opus 5 $0.00041 $0.01175
Sonnet 5 $0.00016 $0.00470
Haiku 4.5 $0.00008 $0.00235

Measured 5d ago against content hash 364234583986, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-agent-memory 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 5d 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/audit-agent-memory/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Agent Memory

Audit one agent's project memory directory for four categories of hygiene issues. Produces a structured advisory report with recommended actions. Does not modify any files.

If invoked without an argument, report:

Usage: /audit-agent-memory <agent-name>

Example: /audit-agent-memory qa-lead

Provide the agent name (e.g. qa-lead, tech-lead, product-owner) to audit
that agent's project memory directory.

And exit without reading any file.

Process

1. Read Memory

Derive the memory directory path from the argument:

.claude/agent-memory/engineering-leaders-<agent-name>/

Attempt to read .claude/agent-memory/engineering-leaders-<agent-name>/MEMORY.md.

If the directory or MEMORY.md does not exist, report:

No memory directory found at .claude/agent-memory/engineering-leaders-<agent-name>/.
Run /onboard or /onboard-<agent-name> to create one.

And exit.

Glob the directory for all *.md files:

.claude/agent-memory/engineering-leaders-<agent-name>/*.md

Read every *.md file found. Collect:

  • The content of MEMORY.md (used for dead-link detection)
  • The content and byte size of every *.md file (used for Check 4 (size))
  • A list of all *.md file paths found (used for dead-link detection)

2. Run Checks

Run the four checks below against the collected files. Each check records findings independently. A single file can produce findings under multiple checks.

Check 1: State-Like Content

Heuristic: A file contains state-like content if it matches any of the following patterns:

Dated phrases (any of these strings, case-insensitive):

  • as of
  • last quarter
  • last month
  • last sprint
  • this quarter
  • this month
  • this sprint
  • current sprint
  • current phase
  • in progress
  • blocked by
  • Q1, Q2, Q3, Q4 followed by a four-digit year (e.g. Q3 2025)

Enumerated file paths: Three or more lines in the file that match the pattern path/to/file (a sequence of path segments separated by /, not starting with http). Count consecutive or near-consecutive path-formatted lines; if three or more appear in the file, this heuristic triggers. Threshold: 3 or more enumerated paths.

Read the full file on GitHub · 271 lines

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. 5d ago First seen · 271 lines · 81 tokens per session scan A 364234583986

Subscribe to this mod's changes

audit-agent-memory is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 14d ago), licensed MIT. It adds 81 tokens to every session and 2,349 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens