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 adamwstauffer/shidler --skill claude-md-auditgit clone --depth 1 https://github.com/adamwstauffer/shidlerWrote 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/adamwstauffer/shidler/claude-md-audit)<a href="https://agentmods.dev/skills/adamwstauffer/shidler/claude-md-audit"><img src="https://agentmods.dev/badge/skills/adamwstauffer/shidler/claude-md-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/adamwstauffer/shidler/claude-md-audit"><img src="https://agentmods.dev/badge/skills/adamwstauffer/shidler/claude-md-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 49 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00099 | $0.01063 |
| Opus 5 | $0.00049 | $0.00531 |
| Sonnet 5 | $0.00020 | $0.00213 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
claude-md-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 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md + Memory Audit Skill
This repo restructures courses/ often (subject-first renames, archive moves, supersessions). Every restructure risks leaving CLAUDE.md or a memory citing a path that no longer exists. This skill catches that drift on a periodic scan rather than trying to check every commit (the most-skipped kind of rule).
Scope
The canonical instruction + memory surface:
CLAUDE.md(repo root) — the single project instruction file.MEMORY.md— the memory index loaded each session (at~/.claude/projects/C--GitHub-shidler/memory/MEMORY.md).- The memory fact files —
feedback_*.md,project_*.md, etc. in the same dir.
The four checks (run all, in order)
1. Stale references (highest value here)
Extract every path CLAUDE.md and MEMORY.md cite (backtick-quoted paths, links, table "Path" columns) and confirm each resolves in the live tree:
# pull backtick-quoted paths from CLAUDE.md, test each
grep -oE '`[^`]+`' CLAUDE.md | tr -d '`' | grep -E '/|\.md|\.json|\.xlsx|\.py' | sort -u \
| while read p; do [ -e "$p" ] || echo "MISSING: $p"; done
Do the same for MEMORY.md and for any path a fact file names in its body. Flag each miss with the citing file:line and the likely correct path (grep the tree for the basename — a restructure usually moved it, didn't delete it).
2. Cross-file contradictions
Compare claims that appear in more than one place — CLAUDE.md vs. a memory, or two CLAUDE.md sections. Common drift: a stage count, a weight table, a "current vs. archived" status, a naming convention. Quote both sides with file:line. (Example class: CLAUDE.md's "Active Courses" table vs. a project_* memory's description of the same course.)
3. Duplication + bloat
Facts stated in full in two places should live in one home with a pointer from the other (single-sourcing). Flag: a fact duplicated between CLAUDE.md and a memory; a memory that just restates code/git history (which the memory rules say not to store); a CLAUDE.md section that has grown past its usefulness.
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.
- 11d ago First seen · 72 lines · 99 tokens per session scan A ac84cb65030a
claude-md-audit is a skill published in the GitHub repository adamwstauffer/shidler (10 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 1,063 once invoked, about $0.0005 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.
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.
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.…
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…
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.
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…
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.