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.
npx skills add adamlinscott/claude-skills --skill memory-auditgit clone --depth 1 https://github.com/adamlinscott/claude-skillsWrote 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.
[](https://agentmods.dev/skills/adamlinscott/claude-skills/memory-audit)<a href="https://agentmods.dev/skills/adamlinscott/claude-skills/memory-audit"><img src="https://agentmods.dev/badge/skills/adamlinscott/claude-skills/memory-audit/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.
<a href="https://agentmods.dev/skills/adamlinscott/claude-skills/memory-audit"><img src="https://agentmods.dev/badge/skills/adamlinscott/claude-skills/memory-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01531 |
| Opus 5 | $0.00000 | $0.00766 |
| Sonnet 5 | $0.00000 | $0.00306 |
| Haiku 4.5 | $0.00000 | $0.00153 |
Grade A, and why
memory-audit scanned grade A with 1 finding 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Reliable way to find it: list `~/.claude/projects/` and pick the directory whose decoded name corresponds to the current Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running a memory audit for the user's per-user Claude memory in this project.
Hard rule: this skill produces a report only. Do not edit, rename, move, or delete any memory file. If the user wants to act on findings, that is a separate follow-up turn after they review the report.
This skill focuses on the internal health of the memory directory itself. For how memory interacts with the wider
repo — conflicts with CLAUDE.md, rules that never reach subagent prompts, broken doc links — see /context-audit.
Step 1 — Ask the user which report style they want
Before reading anything, call AskUserQuestion with:
- question: "What kind of memory audit would you like?"
- header: "Report style"
- multiSelect: false
- options:
- label: "Non-technical summary" description: "Plain-English overview for project management or non-engineering review. Each remembered item is described in everyday language with a clear recommendation."
- label: "Technical audit" description: "Full engineering audit: classification, stale-reference checks, orphaned files, and structural smells. For engineers maintaining the memory."
Wait for the answer before continuing. The user's choice determines the report format in Step 5.
Step 2 — Resolve the memory directory
The memory directory lives at ~/.claude/projects/<encoded-cwd>/memory/, where the encoded form replaces drive colons
and path separators with -.
Reliable way to find it: list ~/.claude/projects/ and pick the directory whose decoded name corresponds to the current
working directory. On Windows the path will look like C:\Users\<user>\.claude\projects\C--Users-<user>-...\memory\.
If the directory does not exist, stop and tell the user: "No memory has been recorded for this project yet — there is nothing to audit."
Step 3 — Read everything
- Read
MEMORY.md. - Read every
.mdfile in the directory — both those the index points to and any that are not indexed. Do not assess a memory you have not read. - For each memory, note its declared
typefrom frontmatter (one of: user / feedback / project / reference). - List the directory contents and identify:
- Files in the directory not indexed in
MEMORY.md - Index entries pointing to files that don't exist
- Files in the directory not indexed in
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.
- 8d ago First seen · 130 lines · 0 tokens per session scan A 87bc1db2fa1d
memory-audit is a skill published in the GitHub repository adamlinscott/claude-skills (3 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,531 tokens. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
capture-learnings
Use in the Learn phase at the end of every task, before declaring done - dispatches the learner agent to record what was learned (conventions, pitfalls, reuse points, decisions) to the cross-session store and refresh the committed memory index, then closes the phase. Runs inline on the main thread (it owns the state…
claudehut-init
Use once per project before starting work (or when ClaudeHut reports no codebase index) to bootstrap ClaudeHut for a Java/Spring repository - detects the stack, generates the project memory + index + path-scoped rules, and wires the always-load @import slice. Invoked as /claudehut:claudehut-init. Idempotent.
summer-kb-setup
Install or refresh a service-scoped Summer Framework (io.f8a.summer) knowledge base in the current consumer service's .claude/summer-kb/. Use when a service that depends on Summer needs its local KB, when onboarding a new ewallet service, when asked to "set up / install / refresh the Summer KB", or when Summer was…
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.