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 agentmods add skills/juxt/claude-plugins/code-commentsnpx skills add juxt/claude-plugins --skill code-commentsgit clone --depth 1 https://github.com/juxt/claude-pluginsWhat 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 | $0.00076 | $0.01540 |
| Opus 5 | $0.00038 | $0.00770 |
| Sonnet 5 | $0.00015 | $0.00308 |
| Haiku 4.5 | $0.00008 | $0.00154 |
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 yesterday.
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 — 113 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.
Two kinds of comment
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. Their defaults are opposite, and everything below is about implementation comments unless it says otherwise.
- An interface comment on a public surface exists by default, and is judged on completeness. Parameters, return, errors, preconditions, units, ownership, thread-safety. A caller who has to read the body to find one of those has been failed.
- A non-public surface takes implementation rules whatever its markup — a kdoc on a private function still faces the triggers.
The readers
An implementation comment's reader is a competent developer on this project, arriving at this line in a year, mid-investigation of a different bug. They did not read the commit that added it, do not know a change happened here, and will read this line and the twenty around it — nothing else.
Simulate that reader before there's a comment on the screen, not after.
What each clause rules out:
- "in a year", "did not read the commit" — they have no referent for the change. "Now we…", "instead of…", "this handles the case we hit" say nothing to them.
- "a different bug" — they want one fact and they're leaving. Orientation, summary and section-label comments cost them and give nothing.
- "this line and the twenty around it" — nothing that depends on reading elsewhere. No "phase 2 of teardown".
An interface comment's reader is deciding whether to call this, from the signature and the doc alone, and will not read the body.
The triggers
An implementation comment MUST answer yes to one of these, asked of the code rather than of the comment. None applies → no comment. One per way the code under-determines what the reader does next.
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.
- yesterday 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 4d ago), licensed MIT. It adds 76 tokens to every session and 1,540 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…