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 agentmods add instructions/rewrite-rs/skills/claude-mdgit clone --depth 1 https://github.com/rewrite-rs/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/instructions/rewrite-rs/skills/claude-md)<a href="https://agentmods.dev/instructions/rewrite-rs/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/rewrite-rs/skills/claude-md.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 | $0.01050 | $0.01050 |
| Opus 5 | $0.00525 | $0.00525 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
skills 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Rules for any session that authors, edits, or reviews a skill in this repo. Read
.agents/invocation.md, .agents/install-block.md, and .agents/writing-docs.md
before touching skill content — this file points at them rather than repeating them.
1. Buckets
skills/rust/ (language craft), skills/porting/ (migration),
skills/workflow/ (review, testing, setup, router), and skills/misc/
(occasional setup and audit skills, reached for less often) are promoted.
skills/in-progress/ (public, unshipped) is not promoted.
Every promoted skill must appear in all three of:
README.md.claude-plugin/plugin.json'sskillsarraydocs/<bucket>/<name>.md
A non-promoted skill appears in none of the three. The split that decides which bucket a skill lives in is frequency of use — how often an agent reaches for it — not whether the skill happens to write files into a user's repo.
2. Prose-dominant with verification
Skills teach judgment in prose. Commands inside a skill are inline instructions the
agent runs itself, never shipped runner scripts the skill invokes on the user's
behalf. Every skill where a machine can settle the question it makes ends with a
verification step the agent actually runs — see
.agents/adr/0001-verification-steps-run-cargo.md.
3. Config precedence
A verification step runs at the lint level configured in the target repo.
cargo clippy -- -D warnings is the fallback only when the target repo has no lint
configuration at all. A skill must never override a lint level the user (or an
earlier setup-rust-skills run) deliberately set.
4. One porting language per session
Never author or revise two port-from-* language skills in the same session. See
.agents/adr/0003-one-skill-per-source-language.md for why the set is split by
source language in the first place.
5. No citations in skill files
Sources live in .agents/sources.md, not inside any SKILL.md or docs page.
6. Invocation
See .agents/invocation.md for the full rules on user-invoked versus model-invoked
skills, and for what agrees between the frontmatter flag in Claude Code and the
agents/openai.yaml policy in Codex.
Any skill that writes files into the user's repo is user-invoked, in any
bucket; rust-skills-map is user-invoked without writing files, because it is
a router the user consults directly. The user-invoked skills are therefore
setup-rust-skills and rust-skills-map in workflow/, and
setup-rust-ci and setup-rust-pre-commit in misc/. Every other skill is
model-invoked.
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.
- 5d ago First seen · 96 lines · 1,050 tokens per session scan A 1f3befeecac8
skills CLAUDE.md is an instructions file published in the GitHub repository rewrite-rs/skills (1 stars, last pushed 20d ago), licensed BSD-3-Clause. It adds 1,050 tokens to every session, about $0.0052 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 instructions, from other repositories
pg-aiguide CLAUDE.md
Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands, code style guidelines and python (ingest/).
claude-code-codex-bridge AGENTS.md
Instructions for vladolaru/claude-code-codex-bridge, covering agents.md, repository overview, architecture, repository structure and package layout.
vibe-coding-kit AGENTS.md
Instructions for Junliu1066/vibe-coding-kit, covering vibe-coding-kit 治理宪法 (governance constitution), 一、最高原则, 二、语言与格式, 三、文件命名强制规范 and 四、必须产出的章节（不可跳过）.
Prompt-sensei CLAUDE.md
Instructions for chengzhongwei/Prompt-sensei, covering repository guidance, documentation shape, when changing behavior, related file sweep and host compatibility.
kluris CLAUDE.md
Instructions for ngvoicu/kluris, covering claude.md, what this is, knowledge base, build & test and architecture.
specmint-core AGENTS.md
Instructions for ngvoicu/specmint-core, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.