Borrowing it
Nothing to install: this file belongs to patrickserrano/lacquer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/patrickserrano/lacquer/main/CLAUDE.mdgit 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/instructions/patrickserrano/lacquer/claude-md)<a href="https://agentmods.dev/instructions/patrickserrano/lacquer/claude-md"><img src="https://agentmods.dev/badge/instructions/patrickserrano/lacquer/claude-md/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/instructions/patrickserrano/lacquer/claude-md"><img src="https://agentmods.dev/badge/instructions/patrickserrano/lacquer/claude-md.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 | $0.01859 | $0.01859 |
| Opus 5.5 | $0.00744 | $0.00744 |
| Sonnet 5.5 | $0.00372 | $0.00372 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
lacquer CLAUDE.md 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 4d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on the lacquer
This file governs work on this repository. The rule files it ships —
core/CLAUDE.core.md and profiles/*/CLAUDE.*.md — govern the projects that
receive them, and are mirrored to the site by internal/docsmirror. This one is
not shipped and has no mirror.
The doctor principle applies inward
README's "Proving the checks work" states it plainly, about the checks this tool ships:
CI already tells you whether a check passes; it cannot tell you whether it could fail.
That is why lacquer doctor writes a known-bad fixture and asserts the check
rejects it. The principle is correct and it was not being applied to the code
that produces those checks. Three defects from 2026-09-11, each of which passed a
green test suite:
- A detector keyed on a managed step's name rather than on whether the declared secrets file was written. A project with a correct hand-rolled step under a different name was reported as exposing App Store credentials. It shipped, and was described to a human as a live risk before anyone re-read it.
- The warnings-as-errors gate resolved an xcconfig by walking the component
directory. A lexical walk reaches
.claude/worktrees/...beforeConfig/, so an abandoned worktree's stale copy won. It reported twelve violations against a fully compliant project and would have refused every sync of it. - The same gate refused a declared-but-absent xcodeproj. One project sits in that state deliberately, documented in its own manifest, because it is pre-code. The gate would have blocked the projects least able to act on it.
None was caught by review. Every one was caught by running the thing against reality. Three rules follow, in yield order.
1. A detector does not merge without a fleet dry-run in the pull request
Run it against every managed repository, and paste the output into the PR
under a ## Fleet dry-run heading. CI rejects a pull request that changes a
detector package without one. Render each repository the way CI sees it: a fresh clone with
xcodegen (and any other generator lacquer invokes) hidden from PATH, because sync regenerates
the project otherwise and both sides of the comparison then carry a file CI never has.
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.
- 4d ago Changed · +7 lines · +122 tokens per session 629a2cd5b907
- 6d ago Changed · +2 lines · +54 tokens per session f9c1cbb9f3fb
- 8d ago Changed · +6 lines · +80 tokens per session 778aeae71f94
- 12d ago Changed · +1 lines · +17 tokens per session 29a4e777501a
- 25d ago Changed · +5 lines · +114 tokens per session 47ac30561e08
- 1mo ago Changed · +4 lines · +62 tokens per session 8835afa2bbc3
- 1mo ago First seen · 123 lines · 1,410 tokens per session scan A 00632bb87b8e
lacquer CLAUDE.md is an instructions file published in the GitHub repository patrickserrano/lacquer (4 stars, last pushed 2d ago), licensed MIT. It adds 1,859 tokens to every session, about $0.0074 per session on Opus 5.5. 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 2026-09-12.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).