Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MuhammadUsmanGM/claude-code-best-practicesnpx agentmods add skills/muhammadusmangm/claude-code-best-practices/lint-docsWrote 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/muhammadusmangm/claude-code-best-practices/lint-docs)<a href="https://agentmods.dev/skills/muhammadusmangm/claude-code-best-practices/lint-docs"><img src="https://agentmods.dev/badge/skills/muhammadusmangm/claude-code-best-practices/lint-docs.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 | $0.00055 | $0.00394 |
| Opus 5 | $0.00028 | $0.00197 |
| Sonnet 5 | $0.00011 | $0.00079 |
| Haiku 4.5 | $0.00006 | $0.00039 |
Grade A, and why
lint-docs 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 6d 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
Lint Docs
Run the same three checks CI runs and report pass/fail per check.
Steps
- shellcheck — find every
.shunder the repo and runshellcheckon it.find . -name '*.sh' -not -path './.git/*' -print0 | xargs -0 shellcheck - markdownlint — run
markdownlintonREADME.md,CONTRIBUTING.md,CHANGELOG.md, and everything underguides/,examples/,plugins/,tools/hooks/. Use.markdownlint.jsonat repo root. - lint-claude-md — run
bash tools/lint-claude-md.shagainst everyexamples/claude-md-*.mdtemplate and the repo's ownCLAUDE.md.
Output
Print a single summary table, one row per check:
| Check | Status | Details |
|---|
If any check fails, print the first 20 lines of its output below the table and stop. Do not try to auto-fix unless the user asks.
Rules
- If
shellcheckormarkdownlintisn't installed, say so and skip that check — don't silently pass. - Do not modify files. This skill is diagnostic only.
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.
- 6d ago First seen · 38 lines · 55 tokens per session scan A be23428c6714
lint-docs is a skill published in the GitHub repository MuhammadUsmanGM/claude-code-best-practices (78 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 394 once invoked, about $0.0003 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.
Other skills, from other repositories
dart-language
Dart 3.x language feature standards: null safety, records, sealed classes, switch pattern matching, extensions, and async/await. Use when using !, ?., ??, late, sealed classes, record types, switch expressions, or async patterns — and before introducing any new Dart 3.x construct to confirm the modern idiomatic…
flutter-auto-route-navigation
Implement typed routing, nested routes, and auth guards using autoroute in Flutter. Use when the task explicitly uses autoroute or its generated router; defer generic deep-link setup and other routing libraries.
flutter-dependency-injection
Configure service locator setup using injectable and getit in Flutter. Use when wiring dependency injection with getit or injectable.
flutter-getx-state-management
Implement reactive state with GetX controllers, bindings, and observables in Flutter. Use when managing app state with GetxController, Obx, GetBuilder, or dependency lifecycle—not unit tests for existing controllers.
dart-best-practices
Dart code quality conventions: naming, const/final/var hierarchy, single quotes, trailing commas, collection idioms, tear-offs, and import organization. Use only for Dart style-focused changes or reviews; never activate for configuration-only lint setup, unrelated feature work, or widget tests.
dart-tooling
Dart static analysis, linting, formatting, and code-generation standards. Use only for analysisoptions.yaml, buildrunner, dart format, DCM, lefthook, or analyze/format CI failures; defer Dart language, null-safety, Flutter tests, and generic CI questions.