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 why-commentsgit 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/why-comments)<a href="https://agentmods.dev/skills/mikestangdevs/craft-skills/why-comments"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/why-comments/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/why-comments"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/why-comments.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 | $0.00130 | $0.01327 |
| Opus 5.5 | $0.00052 | $0.00531 |
| Sonnet 5.5 | $0.00026 | $0.00265 |
| Haiku 4.5 | $0.00013 | $0.00133 |
Grade A, and why
why-comments 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Why Comments
The failure mode this fixes
Comments fail in two opposite directions. Agents (and tired humans) write narration — // loop over the users, // call the API — that restates what the code already says, goes stale the moment the code changes, and trains every reader to skip comments entirely. Meanwhile the one thing a comment can do that code can't — record why — goes unwritten: why the retry is 3 and not 5, why this runs before that, why the obvious approach was tried and reverted. Six months later someone "simplifies" the workaround and reintroduces the bug it guarded against.
This skill inverts the ratio: delete the whats, keep and sharpen the whys, and add a why where surprising code has none.
When to Use This Skill
- A file is full of comments that just narrate the next line
- Load-bearing or surprising code (a magic value, an odd ordering, a deliberately "wrong-looking" approach) has no explanation
- You're reviewing AI-generated code — agents over-narrate and under-justify
explain-backflagged a chunkUNJUSTIFIEDand the justification, once found, should be written down- A comment and the code beneath it disagree (the comment went stale)
Don't use when: the comments are API documentation (docstrings, JSDoc, godoc) — those describe a contract for consumers and are a different job, judged by different rules. And don't add a why where the code is genuinely self-evident; a comment on the obvious is noise wearing a justification.
Instructions
1. Classify every comment in scope
Walk the comments and tag each one:
- WHAT — restates the code (
// check if the user is activeaboveif (user.isActive)) - WHY — states a reason, constraint, or history the code can't show (
// gateway rate-limits at 10 rps; see INC-482) - CONTRACT — docstring/API documentation for consumers → out of scope, leave it
- CORPSE — commented-out code → that's
delete-thisterritory; version control already remembers it - STALE — describes code that no longer matches → either fix it to the current truth or delete it; a wrong comment is worse than none
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.
- 1mo ago First seen · 86 lines · 130 tokens per session scan A 3de14c7bc6a2
why-comments is a skill published in the GitHub repository mikestangdevs/craft-skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 130 tokens to every session and 1,327 once invoked, about $0.0005 per session on Opus 5.5. 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.
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…
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…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.