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/chucklever/cel-kdev/code-commentsnpx skills add chucklever/cel-kdev --skill code-commentsgit clone --depth 1 https://github.com/chucklever/cel-kdevWhat 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 | $0.00109 | $0.03964 |
| Opus 5 | $0.00055 | $0.01982 |
| Sonnet 5 | $0.00022 | $0.00793 |
| Haiku 4.5 | $0.00011 | $0.00396 |
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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code comments: voice and verbosity
Core principle
The first tool for making code understandable is the code, not the comment. Write the function so its working is obvious -- by naming, structure, decomposition, named constants -- and most comments become unnecessary before you type them. Kernel coding-style is emphatic: "it's much better to write the code so that the working is obvious." A comment is the fallback for what the code cannot be made to carry, not the first move.
For the residue that naming and structure cannot express -- an intent, a rationale, a load-bearing invariant, a hazard -- say the non-obvious thing and stop. A comment that restates the code has a cost: it adds maintenance and goes stale the first time the code changes underneath it.
Start at zero
The starting state is no comments. Not "comment as you go, then prune" -- commenting as you go produces narration, and pruning your own narration is the check that never happens. Work in this order:
- Write the code complete and bare. No comments at all, not even placeholders. Name things precisely while you do it.
- Reread it as someone who has never seen it. Note where you actually stumble: a constant with no story, an ordering that looks arbitrary, a branch whose reason is offstage.
- Fix what the code can fix. Each stumble gets the code-first treatment below before it gets a comment.
- Add comments only for what survives -- the always-comment floor, plus the facts step 2 surfaced that step 3 could not absorb.
Every comment is now an addition you chose and can name a reason for. If you cannot say which floor item or which surviving fact a comment covers, it does not go in.
Entering mid-stream: when the code is already drafted and already carries comments, delete the ones you wrote and rejoin at step 2. Comments that were in the file before you touched it are the reader's context, not yours to defend -- judging those is review, and references/reviewing.md governs it.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 361 lines · 109 tokens per session scan A a2d2bc420458
code-comments is a skill published in the GitHub repository chucklever/cel-kdev (2 stars, last pushed 4d ago), licensed MIT. It adds 109 tokens to every session and 3,964 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
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…