rust-doctor: Skill for Claude Code

.claude/skills/rule-admit/SKILL.md

rule-admit is a skill for Claude Code from arthjean/rust-doctor. It costs 98 tokens per session (2,239 once invoked), scanned A, original, Apache-2.0.

A procedure for adding one Clippy lint or built-in detector to rust-doctor’s catalog. Clippy is Rust’s collection of code-quality checks, and a fixture is a test file designed to trigger one check.

In plain words
What is it for?
Use it to document what a rule detects, define its category and tier, create a triggering fixture, add supporting records, and update all required catalog data.
Why use it?
It prevents the rule catalog, test fixtures, evidence records, corpus, and manually maintained counters from becoming inconsistent. Tests verify that each admission step was completed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is arthjean/rust-doctor's own configuration. It tells Claude Code how to work on rust-doctor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rust-doctor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arthjean/rust-doctor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arthjean/rust-doctor/main/.claude/skills/rule-admit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/arthjean/rust-doctor

Made for: Claude Code.

Wrote 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.

agentmods badge for rule-admit

README.md
[![agentmods](https://agentmods.dev/badge/skills/arthjean/rust-doctor/rule-admit/github.svg)](https://agentmods.dev/skills/arthjean/rust-doctor/rule-admit)
Your own site
<a href="https://agentmods.dev/skills/arthjean/rust-doctor/rule-admit"><img src="https://agentmods.dev/badge/skills/arthjean/rust-doctor/rule-admit/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.

agentmods 80×15 button for rule-admit

Your own site · 80×15
<a href="https://agentmods.dev/skills/arthjean/rust-doctor/rule-admit"><img src="https://agentmods.dev/badge/skills/arthjean/rust-doctor/rule-admit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,239 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.02239
Opus 5 $0.00049 $0.01120
Sonnet 5 $0.00020 $0.00448
Haiku 4.5 $0.00010 $0.00224

Measured 9d ago against content hash 995e9fdd83cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rule-admit 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 9d 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.

.claude/skills/rule-admit/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Admit one rule

Admission is one rule at a time. The catalog is small enough that every counter around it is written out by hand, so the work is less about the rule than about leaving nothing out of sync. Everything below is enforced by a test: skipping a step fails the suite, it does not slip through.

Read the "Admitting a rule" section of docs/catalog-and-corpus.md and "Invariants the tests enforce" in docs/testing.md first. Verify the suite is green before starting, so that a failure during the run belongs to the rule.

Step 1: Record what the rule catches

Take the toolchain's own description:

clippy-driver -W help | grep <lint-name>

That line is the catches field, verbatim. It has to match, a test compares them. A native detector has no upstream line, so write one sentence naming the pattern, not the fix.

Pick the category and the tier, and check the pair against TIER_WINDOWS in src/policy/catalog/validate.rs. Write help as an instruction to the user: what to do instead, in one sentence, without restating the problem.

Step 2: Build the trigger fixture

The rule needs a place where a test sees it fire. Follow the pattern of the rules admitted before it rather than inventing one.

For a lint whose dimension matches an existing pack, add the triggering form to tests/fixtures/score-credibility/packs/<pack>/src/lib.rs, the quiet counterpart to src/negatives.rs of the same pack, and the expected diagnostic to the pack's oracle.json under positive, with code, category, tier, path, line and occurrences. The packs are panic, performance and concurrency.

Otherwise use the isolated form: a crate under tests/fixtures/rule-scaling-kernel/positive/<kebab-name>/ and an entry in tests/fixtures/rule-scaling-kernel/oracle.json under rules, carrying id, category, help, clippy_default, message, positive_fixture and its spans.

The negative form matters as much as the positive one. A rule with no recorded silence is a rule nobody has checked for over-reach.

Read the full file on GitHub · 202 lines

Changes

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.

  1. 9d ago First seen · 202 lines · 98 tokens per session scan A 995e9fdd83cf

Subscribe to this mod's changes

rule-admit is a skill published in the GitHub repository arthjean/rust-doctor (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 98 tokens to every session and 2,239 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 2026-08-30.