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 mikestangdevs/craft-skills --skill boyscoutgit clone --depth 1 https://github.com/mikestangdevs/craft-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/skills/mikestangdevs/craft-skills/boyscout)<a href="https://agentmods.dev/skills/mikestangdevs/craft-skills/boyscout"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/boyscout/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/mikestangdevs/craft-skills/boyscout"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/boyscout.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 | $0.00107 | $0.01154 |
| Opus 5 | $0.00053 | $0.00577 |
| Sonnet 5 | $0.00021 | $0.00231 |
| Haiku 4.5 | $0.00011 | $0.00115 |
Grade A, and why
boyscout 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boy Scout
The failure mode this fixes
Two opposite failures rot codebases. One: never cleaning up, so entropy compounds until the file is a no-go zone. The other: a "quick change" balloons into a 600-line refactor that's impossible to review and ships three bugs. Agents swing wildly between both — either touching nothing around the change or rewriting the whole file uninvited.
The Boy Scout Rule threads the needle: leave the code a little better than you found it. Small, bounded, in-scope, separate from the behavior change. This skill enforces the little — disciplined cleanup, not a crusade.
When to Use This Skill
- You're editing an existing file to make a change (any non-trivial edit)
- You notice something adjacent that's mildly wrong (a vague name, a dead line, a muddy condition)
- A reviewer asked "while you're in there, can you also..."
Don't use when: the file is brand new (nothing to clean), or the cleanup is large enough to deserve its own PR. If cleanup would exceed roughly a third of the size of your actual change, stop and file it as separate work — the cleanup is the tip, not the meal. For a deliberate dead-code sweep across a module, use delete-this instead — this skill is only for small, opportunistic, in-scope cleanup riding along with a change you're already making.
Instructions
1. Make your real change first
Do the thing you came to do. Get it working and verified. The cleanup is a tip, not the meal — never let it block or bloat the actual change.
2. Scan only what you touched (the blast radius)
Look at the functions and lines your change touched, plus their immediate neighbors. Do not scan the whole file for sins — that's how scope explodes. The rule applies to the campsite you used, not the whole forest.
3. Pick improvements that pass the cheapness test
An improvement qualifies only if it is all of:
- Small — a name, a deleted dead line, one extracted helper, a clarified boolean, a fixed comment
- Safe — provably behavior-preserving (no logic change)
- In-scope — adjacent to your change, in code you already had to understand
- Self-evident in review — a reviewer sees instantly why it's better
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.
- 9d ago First seen · 81 lines · 107 tokens per session scan A eec4d72299ef
boyscout is a skill published in the GitHub repository mikestangdevs/craft-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 107 tokens to every session and 1,154 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 2026-08-31.
Other skills, from other repositories
plumb-line-audit
Use when auditing a diff or repository against the plumb-line principles — finds laundered uncertainty, boundary leaks, hardcoded priors, overstated maturity, outputs lacking recorded lineage, and baseline drift with no explanation. Read-only: it reports, never auto-fixes.
Tech Debt Auditor
Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.
craft-audit
The front door to the craft skills — a whole-project production-readiness orchestrator that drives the ten per-domain craft skills (ux, frontend, backend, db, security, infra, observability, testing, lint, ai) instead of auditing one surface at a time. It discovers the project's shape, plans an audit per surface, and…
craft-backend
The Craftsman standard for building and reviewing backend code — API routes, request validation, the authentication boundary, service/business logic, error handling, route rate-limit middleware, third-party integrations, and background jobs. Use this WHENEVER the work touches the server side: adding or reviewing a…
code-consolidation
This skill should be used when the user asks to "find duplicated code", "map responsibilities", "consolidate code", "find code sprawl", "analyze duplication", "create consolidation plan", or mentions "código duplicado", "responsabilidades espalhadas", "consolidar". Analyzes codebases to identify scattered…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.