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/lexfrei/ccc/replynpx skills add lexfrei/ccc --skill replygit clone --depth 1 https://github.com/lexfrei/cccWhat 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 | $0.00090 | $0.00981 |
| Opus 5 | $0.00045 | $0.00491 |
| Sonnet 5 | $0.00018 | $0.00196 |
| Haiku 4.5 | $0.00009 | $0.00098 |
Grade A, and why
reply 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A review reply is prose sent into a public, permanently archived thread. The mechanics are three commands; the failure modes are all in the content, so the content gates come first.
Gate: is a reply the right vehicle?
- Review comments are answered in-thread. Fixed code is not — a new version of the series goes out as a new thread (lkml:submit). Never attach or inline corrected patches in a reply.
- Answer the review before reposting: do not send a new version while the discussion about the current one is still ongoing, unless a reviewer directly asks for it.
- Every reviewer comment gets a response — agreed-and-will-fix, a reasoned pushback, or a clarifying question. Silently dropping a point reads as ignoring the reviewer, and ignoring reviewers is how submissions start being ignored.
Build the reply
Fetch the thread mbox (lkml:lore) and take from the mail being answered: its exact Message-ID:, its exact Subject:, its From:, and the full recipient set. Never guess or reconstruct a Message-ID.
Write the reply to a file with a header block:
Subject: Re: [PATCH net-next 2/3] net: dsa: mt7530: example subject copied exactly
> quoted fragment of the reviewer's point, trimmed to what is answered
> only
Response to that point.
> next quoted point
Response.
Formatting rules for the body:
- Interleaved replies only. Quote a fragment with
>, answer under it, repeat. Top-posting (answer above full quote) marks the mail as not worth reading. - Trim quotes. Keep only the lines being answered; delete the rest of the quoted mail, including the signature and the diff, unless a specific hunk is discussed.
- Hard-wrap body text at about 72 columns. Kernel mail is plain-text with real line breaks — the opposite of markdown-renderer habits. No HTML, no attachments, no links where text will do.
- Answer in the order the points were raised; one mail per parent mail being answered, not one mail per point.
Tone that works on kernel lists
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.
- 2d ago First seen · 66 lines · 90 tokens per session scan A 241749044bc5
reply is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 90 tokens to every session and 981 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…