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-slicenpx skills add Pinperepette/context-kernel --skill kernel-slicegit 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 | $0.00068 | $0.00665 |
| Opus 5 | $0.00034 | $0.00332 |
| Sonnet 5 | $0.00014 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
kernel-slice scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
kernel-slice — proiezione formale del codice
Quando serve ragionare su un simbolo specifico (una funzione, una classe, un tipo) dentro un file Python o Go grande, non leggere l'intero file: estrai solo la sua chiusura di raggiungibilita' sul grafo def-use. Tutto il resto (funzioni morte, import inutilizzati, classi scollegate) non puo' cambiare il comportamento del target, quindi e' rumore per il contesto.
Come usarlo
- Pi: chiama il tool nativo
kernel_sliceconfileesymbols. - Claude Code: esegui via Bash lo script incluso:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/kernel-slice/scripts/slice.py" <file.(py|go)> <simbolo> [<simbolo2> ...]
Negli altri harness risolvi scripts/slice.py relativamente alla directory
di questa skill. Lo script stampa solo le definizioni top-level raggiungibili
dai target, piu' gli import effettivamente usati. Ragiona su quell'output invece
del file intero.
Garanzia
Rispetto ai simboli chiesti, il comportamento di un simbolo dipende solo dalle sue dipendenze transitive:
- Python (
.py): answer-preserving per costruzione ed ESATTO — l'AST della stdlib da' l'insieme d'uso preciso di ogni unita' top-level. - Go (
.go): answer-preserving conservativo — senza un parser Go nella stdlib, l'insieme d'uso e' la sovra-approssimazione "tutti gli identificatori del corpo" (stringhe e commenti mascherati): la fetta puo' tenere piu' del minimo, ma non lascia mai fuori una dipendenza del target. Confine delle unita' = convenzione gofmt (dichiarazioni a colonna 0); se lo split non e' fidato (graffe sbilanciate su codice non-gofmt) ritorna il file intero.
Se un simbolo non e' riconosciuto, o il file non e' .py/.go, lo script
ritorna il file intero (fail-safe): non perde mai informazione rilevante.
Quando NON usarlo
- Se ti serve una visione d'insieme del file (non un simbolo specifico).
- Se il file e' piccolo (< ~100 righe): leggerlo intero costa poco.
What ships with it
1 file 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.
- 2d ago First seen · 51 lines · 68 tokens per session scan A 81b80d59cf9e
kernel-slice is a skill published in the GitHub repository Pinperepette/context-kernel (24 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 665 once invoked, about $0.0003 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…