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 patrickserrano/lacquer --skill claudemd-reviewgit clone --depth 1 https://github.com/patrickserrano/lacquerWrote 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/patrickserrano/lacquer/claudemd-review)<a href="https://agentmods.dev/skills/patrickserrano/lacquer/claudemd-review"><img src="https://agentmods.dev/badge/skills/patrickserrano/lacquer/claudemd-review.svg" alt="Measured on agentmods" 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 | $0.00127 | $0.00578 |
| Opus 5 | $0.00063 | $0.00289 |
| Sonnet 5 | $0.00025 | $0.00116 |
| Haiku 4.5 | $0.00013 | $0.00058 |
Grade A, and why
claudemd-review 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.
What it actually says
CLAUDE.md Review
A quick self-check, not a pipeline: read back over this conversation, find places where the human corrected something a project rule should have already covered, and propose a small, bounded edit. Nothing here gets applied without the human reviewing it first.
Process
- Scan this conversation for corrections, "no, actually", or repeated
clarifications — the same signal
skill-tuning-loop's Mine stage looks for in past sessions, except you already have the transcript in context. - For each one, classify it:
- Already covered, ignored anyway — the relevant CLAUDE.md already says this; the fix is emphasis or clarity, not new content.
- Genuinely missing — no existing rule addresses it; a new line would have prevented the correction.
- One-off — specific to this task, not a durable project convention. Don't propose an edit for this; CLAUDE.md is for what generalizes.
- Propose a MINIMAL diff for the "genuinely missing" and "ignored anyway" cases only. Match the file's existing voice and structure — don't restructure sections that aren't implicated. State the rule concretely (name the specific convention), not "follow best practices."
- Present the diff, don't apply it. Show the human the proposed addition and why (quote the correction that motivated it). They edit the file, not you — CLAUDE.md is read on every session for every task in the project; a bad edit here is a bad edit everywhere.
When to reach for skill-tuning-loop instead
This skill only ever sees one conversation, so it can mistake a one-off
correction for a durable pattern. If the same friction keeps showing up
across sessions and you want a validated, evidence-gated proposal rather
than a quick check, that's what skill-tuning-loop is for.
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 · 49 lines · 127 tokens per session scan A 979f52fdb99b
claudemd-review is a skill published in the GitHub repository patrickserrano/lacquer (3 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 578 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 2026-08-31.
Other skills, from other repositories
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
printing-press-score
Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.
printing-press
Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a…
gograph
Go repository intelligence for Claude Code. Use when reading, navigating, editing, reviewing, or refactoring a Go codebase. Exposes 64 query, analysis, and workflow capabilities through the local gograph MCP server, including bounded first-call exploration, AST-aware call graphs, blast-radius analysis, impact, and…
performance
A guide to measuring and improving the speed and resource use of Go programs. It explains benchmarks and profiling, which records where a program spends time or memory.