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/pinperepette/context-kernel/kernel-opsnpx skills add Pinperepette/context-kernel --skill kernel-opsgit clone --depth 1 https://github.com/Pinperepette/context-kernelWhat 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 | $0.00207 | $0.00862 |
| Opus 5 | $0.00103 | $0.00431 |
| Sonnet 5 | $0.00041 | $0.00172 |
| Haiku 4.5 | $0.00021 | $0.00086 |
Grade A, and why
kernel-ops 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kernel-ops — la superficie operativa del context-kernel a parole
Questa skill è il gemello a linguaggio naturale dei comandi /ck-*: stessa
funzione, stessi script, ma raggiungibile dicendo cosa vuoi invece di ricordare
la sintassi. Gli script vivono sotto ${CLAUDE_PLUGIN_ROOT}/hooks/ (con la via
plugin) oppure, per l'install manuale, nella cartella hooks/ del plugin —
risolvi il path una volta e riusalo.
Principio (non tradire la filosofia)
Il plugin non fa mai tuning silenzioso. Questa skill può leggere e
diagnosticare liberamente, ma tutto ciò che scrive stato va fatto solo su
richiesta esplicita dell'utente, annunciando cosa sta per cambiare:
apply-rates (relax-only), write-priors (add-only), charter clear,
savings reset-canary. Nel dubbio: mostra, non attuare.
Instradamento dell'intento
Capisci cosa chiede l'utente e lancia il comando corrispondente (poi sintetizza l'output, non incollare referti lunghi):
| L'utente vuole… | Comando |
|---|---|
| stato/colpo d'occhio (risparmio, canary, coda A/B, carta) | savings.py + ab_verify.py --status + charter.py get |
| salute dell'installazione (health-check) | doctor.py |
| report risparmio token | savings.py (--html [path] per la pagina) |
| acquietare il canary dopo indagine (esplicito) | savings.py --reset-canary |
| giudicare i campioni A/B | ab_verify.py (--status, --dry-run, --limit N) |
| recuperare un output parcheggiato | recall.py --search REGEX | recall.py <chiave> --grep/--lines |
| vedere/rinfrescare/azzerare la carta del task | charter.py get | refresh | clear |
| smoke test della compressione | smoke.py generate poi smoke.py check |
| rilevanza rivelata (T5), solo report | revealed.py --aggregate |
| attuare tassi/prior appresi (esplicito) | revealed.py --aggregate --apply-rates | --write-priors |
Tutti eseguibili con python3 <hooks>/<script>. Se l'utente preferisce la forma
digitata, gli stessi passi sono i comandi /ck-status, /ck-doctor,
/ck-savings, /ck-verify, /ck-recall, /ck-charter, /ck-smoke, /ck-tune.
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 · 45 lines · 0 tokens per session scan A 9224db6d8870
kernel-ops is a skill published in the GitHub repository Pinperepette/context-kernel (24 stars, last pushed 1mo ago), licensed MIT. It adds 207 tokens to every session and 862 once invoked, about $0.0010 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 2026-08-30.
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…