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 skills add JordanCoin/codingskills --skill boy-scout-rulegit clone --depth 1 https://github.com/JordanCoin/codingskillsWrote 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/jordancoin/codingskills/boy-scout-rule)<a href="https://agentmods.dev/skills/jordancoin/codingskills/boy-scout-rule"><img src="https://agentmods.dev/badge/skills/jordancoin/codingskills/boy-scout-rule/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/skills/jordancoin/codingskills/boy-scout-rule"><img src="https://agentmods.dev/badge/skills/jordancoin/codingskills/boy-scout-rule.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 | $0.00066 | $0.00902 |
| Opus 5 | $0.00033 | $0.00451 |
| Sonnet 5 | $0.00013 | $0.00180 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
boy-scout-rule 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 10d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boy Scout Rule
Before Applying
If .agents/stack-context.md exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
Principle
Leave every file you touch a little better than you found it. Not a lot better — a little better. Incremental improvement compounds into a clean codebase over time.
Why This Matters in Production
Codebases don't rot overnight. They degrade one shortcut at a time — a hardcoded value here, a skipped rename there, a TODO that lives for three years. The Boy Scout Rule is the antidote: it makes improvement the default, not a scheduled event.
Teams that practice this never need "cleanup sprints." Their code stays healthy because maintenance happens continuously, embedded in regular feature work.
But this only works with discipline: improvements must be small, safe, and scoped. A "cleanup" that touches 40 files and breaks two features is worse than leaving the mess.
Rules
- Fix what you see, within scope. If you open a file to fix a bug and notice a misleading variable name, rename it. If you see a dead import, remove it. These are safe, low-risk improvements.
- Keep cleanups in separate commits. A feature commit should contain the feature. A cleanup commit should contain the cleanup. Mixing them makes code review harder and reverts dangerous.
- Don't refactor what you don't understand. If you open an unfamiliar file and something looks wrong, investigate before "fixing" it. What looks like dead code might be a critical fallback. What looks like a typo might be intentional.
- Scope your improvements. Boy Scout Rule means fixing a confusing name or adding a missing type annotation. It does not mean redesigning a module you happened to walk past.
- Leave a trail. If you notice a problem too large to fix in passing, create an issue or add a
TODO(ticket-number)so it doesn't get forgotten.
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.
- 10d ago First seen · 70 lines · 66 tokens per session scan A e6fcc685f0e5
boy-scout-rule is a skill published in the GitHub repository JordanCoin/codingskills (7 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 902 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 2026-08-31.
Other skills, from other repositories
karpathy-coding-principles
Use when andrej Karpathy's 4 coding principles — think before coding, simplicity first, surgical changes, goal-driven execution. Use when coding, reviewing code quality, reducing overengineering,.
refactor
Automated iterative code refactoring with swarm-orchestrated specialist agents including deep codebase discovery, confidence-scored code review, and security analysis. Use this skill when the user wants to improve existing code quality, clean up messy code, restructure, simplify, reduce tech debt, or perform…
uncle-bob-craft
Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.
delphi-clean-code-solid
Diretrizes de SOLID, Clean Code e padrões de nomenclatura para classes, interfaces, métodos e variáveis em projetos Delphi.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…