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/patch-statusnpx skills add lexfrei/ccc --skill patch-statusgit 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 | $0.00100 | $0.00907 |
| Opus 5 | $0.00050 | $0.00453 |
| Sonnet 5 | $0.00020 | $0.00181 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
patch-status scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --silent "https://patchwork.kernel.org/api/1.2/patches/?project=netdevbpf&msgid=<message-id>" | jq '.[0] | {state, delegate: .delegate.username, web: .web_url}' How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patchwork tracks what maintainers will do with a patch; the mailing list tracks what people said about it. Check both before concluding anything: a thread with zero replies can still be accepted, and a thread full of praise can sit at changes-requested.
Query by Message-ID
curl --silent "https://patchwork.kernel.org/api/1.2/patches/?project=netdevbpf&msgid=<message-id>" | jq '.[0] | {state, delegate: .delegate.username, web: .web_url}'
<message-id>is bare, without angle brackets — the ID of a patch mail (1/N,2/N, ...). Cover letters are not patches; querying a0/NID returns an empty list.project=netdevbpfcovers netdev and bpf. Other kernel subsystems have their own project slugs on the same instance — list them viahttps://patchwork.kernel.org/api/1.2/projects/and match bylist_email. Some subsystems do not use patchwork at all; an empty result for every patch of a series means look at the thread and the maintainer's git tree instead.- Other projects run their own instances with the same API (U-Boot lives on
patchwork.ozlabs.org,project=uboot).
What the states mean
| state | meaning | your move |
|---|---|---|
new |
in the queue, nobody triaged it | wait |
under-review |
a maintainer is looking | wait |
changes-requested |
review asked for changes | answer every comment in-thread, then new version as a new thread |
superseded |
a newer version of the series replaced it | check the newest version instead |
accepted / queued |
applied to the maintainer tree | done; netdev also sends an "applied" mail to the thread |
rejected / not-applicable |
will not be taken as-is | read the thread for the reason before doing anything |
deferred / awaiting-upstream |
parked on something external | find what it waits for in the thread |
delegate set to a maintainer (e.g. netdev) means the series is in that queue — a good sign, not a request for action.
A reply in the thread reading pw-bot: cr (or pw-bot: changes-requested) is a bot command that moved the series to changes-requested. Treat it exactly like the state: the next posting is a new version in a new thread, never a reply with fixed patches.
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 · 45 lines · 100 tokens per session scan A c42e4d07b1e6
patch-status is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 100 tokens to every session and 907 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…