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 juxt/claude-plugins --skill code-commentsgit clone --depth 1 https://github.com/juxt/claude-pluginsWrote 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/juxt/claude-plugins/code-comments)<a href="https://agentmods.dev/skills/juxt/claude-plugins/code-comments"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/code-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/juxt/claude-plugins/code-comments"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/code-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 | $0.00090 | $0.02802 |
| Opus 5.5 | $0.00036 | $0.01121 |
| Sonnet 5.5 | $0.00018 | $0.00560 |
| Haiku 4.5 | $0.00009 | $0.00280 |
Grade A, and why
code-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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chalk Code Comments — What Earns a Comment
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
You SHOULD NOT write any code comments
The code is the artefact; a comment is a second copy of part of it that nothing verifies. No compiler checks it, no test fails when it drifts, and a reader who trusts a stale comment ends up worse off than one who had nothing. Everything below this section is the narrow set of cases where that cost is worth paying.
-
Where a comment is tempting, change the code instead. Kernighan and Plauger's rule from The Elements of Programming Style is still the first move: don't comment bad code — rewrite it. The Linux kernel coding style puts the same thing as a prohibition — never explain in a comment how your code works, because it is better to write code whose working is obvious.
-
The reader already assumes you chose this deliberately and with care. They apply Chesterton's fence before they touch it, so you MUST NOT spend a comment defending the code against a reader who was never sceptical. Explaining a constraint the reader can't see is a different act from justifying yourself, and only the first has an audience.
-
A comment that does survive is a Chalk artefact. It MUST be written in the chalk voice —
chalk:voicecarries the register, the audience and the rule that two propositions in a relation take a mindmap rather than prose.
Interface comments are the standing exception
An interface comment says what a caller needs in order to use the thing without reading its body. An implementation comment says what the code inside it doesn't already say.
The default above is about implementation comments, and so is everything below unless it says otherwise.
- An interface comment on a public surface exists by default, and is judged on completeness rather than on necessity. Parameters, return, errors, preconditions, units, ownership, thread-safety — Diátaxis reference, held to the standard of Javadoc's own doc-comment conventions. A caller who has to read the body to find one of those has been failed. You SHOULD NOT document what the signature already expresses.
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 Changed · -30 lines 2f40f38497ab
- 1mo ago Changed · +36 lines 5e88c9d38601
- 1mo ago Changed · +68 lines · +14 tokens per session 9bc170fbf588
- 1mo ago Changed · +10 lines df24b4e8356e
- 1mo ago First seen · 113 lines · 76 tokens per session scan A 45b0d8bc942d
code-comments is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 2,802 once invoked, about $0.0004 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…