memory-audit

memory-audit is a skill for Claude Code from vergil-project/vergil-claude-plugin. It costs 73 tokens per session (786 once invoked), scanned A, original, MIT.

A guided review process for memory files used by a coding agent. It checks whether saved notes still match the codebase and asks the human before changing them.

In plain words
What is it for?
It is for auditing MEMORY.md and related files, checking referenced paths and tools, judging each entry's accuracy, and deciding whether to keep, update, move, or remove it.
Why use it?
It helps find outdated, orphaned, or incorrect project memories without silently deleting or rewriting them.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the vergil plugin — 15 skills, 1 agent, 2 hooks shipped together

Good fit It is for auditing MEMORY.md and related files, checking referenced paths and tools, judging each entry's accuracy, and deciding whether to keep, update, move, or remove it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vergil-project/vergil-claude-plugin/memory-audit
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 vergil-project/vergil-claude-plugin --skill memory-audit
Clone the repo
git clone --depth 1 https://github.com/vergil-project/vergil-claude-plugin

Made for: Claude Code.

Or install vergil, the plugin that ships this one along with the rest of its 15 skills, 1 agent, 2 hooks.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/memory-audit.svg)](https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/memory-audit)
Your own site
<a href="https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/memory-audit"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/memory-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 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 $0.00073 $0.00786
Opus 5 $0.00036 $0.00393
Sonnet 5 $0.00015 $0.00157
Haiku 4.5 $0.00007 $0.00079

Measured 8d ago against content hash 358888c9f9d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

memory-audit 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 8d 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/memory-audit/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Audit

Structured walk-through of a project's memory files. For each file, verify its claims against the codebase, suggest a disposition, and wait for the human to decide before acting.

Workflow

1. Inventory

Read MEMORY.md and list all .md files in the memory directory. Report:

  • File count and breakdown by type (feedback, project, reference, user, handoff).
  • Last-modified date for each file.
  • Orphan files — present in the directory but not indexed in MEMORY.md.
  • Broken links — entries in MEMORY.md pointing to files that no longer exist.

2. Walk-through

Present each memory file one at a time. For each:

Show: Name, type (from frontmatter), and content. Summarize if the file exceeds ~30 lines.

Verify: Actively check claims against the codebase:

  • If the memory references a file path, check it exists.
  • If it references a function, pattern, or convention, grep for it.
  • If it references a tool or command, check if it is on PATH.

Present verification findings alongside the content.

Assess: Based on verification results, is this entry still accurate?

Suggest disposition with reasoning — one of:

Disposition When to use
Keep Still accurate, correctly scoped to this repo.
Update Substance is right, content needs refreshing.
Relocate → global CLAUDE.md Cross-repo preference, not repo-specific.
Relocate → plugin/skill issue About vergil-tooling suite behavior.
Delete Stale, redundant, or no longer relevant.

3. Human decides

Wait for the human to confirm or override the suggestion. Do not proceed until the human responds. One file at a time — no batching.

4. Execute

After the human decides:

  • Keep: No change.
  • Update: Edit the file. Show the diff before and after.
  • Relocate → global CLAUDE.md: Draft the addition to ~/.claude/CLAUDE.md. Show the draft. Write on approval.
  • Relocate → plugin/skill issue: Draft the issue body. Show the draft. On approval, create it with vrg-triage-create --kind triage --title … --body-file <tmp> — an unlinked intake issue in the org .github (the tool's default) that triage-review routes to an epic later.
  • Delete: Remove the file and its index entry from MEMORY.md.

Read the full file on GitHub · 91 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. 8d ago First seen · 91 lines · 73 tokens per session scan A 358888c9f9d5

Subscribe to this mod's changes

memory-audit is a skill published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 786 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

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

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens