Borrowing it
Nothing to install: this file belongs to jdutton/vibe-agent-toolkit. 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/jdutton/vibe-agent-toolkit/main/CLAUDE.mdgit clone --depth 1 https://github.com/jdutton/vibe-agent-toolkitWrote 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/jdutton/vibe-agent-toolkit/claude-md)<a href="https://agentmods.dev/instructions/jdutton/vibe-agent-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/jdutton/vibe-agent-toolkit/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/jdutton/vibe-agent-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/jdutton/vibe-agent-toolkit/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 | $0.04168 | $0.04168 |
| Opus 5.5 | $0.01667 | $0.01667 |
| Sonnet 5.5 | $0.00834 | $0.00834 |
| Haiku 4.5 | $0.00417 | $0.00417 |
Grade A, and why
vibe-agent-toolkit 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 19d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Development Guidelines
Rules for anyone (human or agent) working on vibe-agent-toolkit — a TypeScript monorepo for
building, testing and distributing portable AI agents and skills. Architecture and every how-to
live in docs/; this file carries only rules that prevent a specific mistake.
Convention: every rule here ends with (enforced by: <check>) or (not enforced) — if you add
a rule, tag it; if you add an enforcer, retag the rule.
Pre-1.0 policy — backward compatibility is a bug
While the version is 0.x: no compatibility layers, no deprecation shims, no re-exports "for
convenience", no old API kept beside a new one. Make the breaking change, delete the old code, force
consumers to update, and record it under Breaking in the changelog. Semantic versioning with
deprecation cycles starts at 1.0. (not enforced)
No version constants — the npm package version is the only version
No hand-maintained integer decides whether stored data is still valid: no CACHE_VERSION,
SCHEMA_VERSION, *_REVISION, no z.literal(<n>) on a version field, no schema:/v1alpha
label in VAT's own output. Derive the fact from the shape itself (a digest of the schema's
declaration, as parseFactsShapeSource() does), validate with a .strict() schema, or invalidate
explicitly by deleting the stored artifact. Any PR that introduces one must say so under its own
heading so it is removed before merge. Not offenders: an external API header value, a real list of
supported versions, a regex that parses versions, a VERSION string in a test fixture. Rationale:
docs/contributing/no-version-constants.md.
(enforced by: local/no-version-literal for the integer shapes; labels and the PR heading are not)
Drift classes — fix the class, never the instance
Each of these grew for months under a green gate and was found only by adversarial review. When one
surfaces, fix it the right way in the same change — one contract, every caller migrated, the
enforcer added — never quiet it with a compat shim, an allowlist entry, a directive, a widened
factor or a TODO. Tells and fixes: docs/contributing/drift-classes.md.
(not enforced)
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.
- 19d ago Changed · +6 tokens per session 6d22294ca5ae
- 1mo ago Changed · -402 lines · -5,201 tokens per session 8c8e8dea0b62
- 1mo ago Changed · +4 lines · +342 tokens per session bb26718080c6
- 1mo ago Changed · +2 lines · +154 tokens per session f131d4a0b285
- 1mo ago Changed · +1 lines · +58 tokens per session e194f2c442cd
- 2mo ago First seen · 632 lines · 8,809 tokens per session scan A 008a1f30121d
vibe-agent-toolkit CLAUDE.md is an instructions file published in the GitHub repository jdutton/vibe-agent-toolkit (2 stars, last pushed today), licensed MIT. It adds 4,168 tokens to every session, about $0.0167 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 2026-08-31.
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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.