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-pipelinenpx skills add Pinperepette/context-kernel --skill kernel-pipelinegit 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 | $0.00069 | $0.00827 |
| Opus 5 | $0.00034 | $0.00413 |
| Sonnet 5 | $0.00014 | $0.00165 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
kernel-pipeline 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kernel-pipeline — C' = T4(T3(T2(T1(C))))
Ogni stadio e' un operatore con un invariante dichiarato. T1 (compressione degli output dei tool) e' ambientale: gli hook la applicano gia'. Questa skill orchestra il resto.
Quando
Bug non banale in repo con molti file. Se il repo e' piccolo o il fix e' ovvio, salta la pipeline: il costo degli stadi deve valere meno del vagare.
Stadi
- T2 — slice del repo (deterministico): segui
kernel-repo-slicecol sintomo. Ottieni il manifest C2. In Pi puoi delegare al tool isolatokernel_scout; in Claude Code all'agentkernel-scout. - T3 — carta del task (semantico, citabile): segui
kernel-invariantssui file di C2. Ottieni la carta C3. In Pi puoi delegare al tool isolatokernel_extractor; in Claude Code all'agentkernel-extractor. - Fix: lavora SOLO da C3 + i file citati. Regola page-fault: se serve un file fuori slice, leggilo e ANNOTA il miss (file + perche' serviva).
- T4 — verifica: ripassa la carta vincolo per vincolo contro il diff.
A campione (fix delicati):
kernel-verifycon Q = il bug, x = i file citati interi, pi(x) = la carta — la risposta cambia? In Pi puoi delegare al tool isolatokernel_verifier; in Claude Code all'agentkernel-verifier.
Telemetria (per la curva rate-distortion)
A fine giro annota quattro numeri nel report:
- rate: file in slice / file scansionati (dal manifest)
- fault: quanti page fault (file fuori slice letti davvero)
- repair: costo dei fault (righe lette fuori slice)
- verdetto T4: vincoli rispettati / violati
Un fault alto con repair basso = la slice era aggressiva ma il modello regge (bene). Vincoli violati non citati = T3 ha perso segnale (male: stringere T3, non allargare T2).
Persistenza (OBBLIGATORIA a fine giro)
Oltre al report, appendi UNA riga JSON per run a ~/.context-kernel-pipeline.jsonl
(e' il dataset della curva rate-distortion). Schema — coi numeri veri del run:
python3 - <<'PYEOF'
import json, os, datetime
rec = {
"ts": datetime.datetime.now().isoformat(timespec="seconds"),
"repo": "/path/del/repo", "scanned": 1415, "slice": 123,
"fault": 2, "repair_righe": 15,
"verdetto": "PASS", "vincoli": "12/12",
"note": "cosa ha morso il fault, se c'e' stato",
}
rec["rate"] = round(1 - rec["slice"] / rec["scanned"], 3)
with open(os.path.expanduser("~/.context-kernel-pipeline.jsonl"), "a") as f:
f.write(json.dumps(rec) + "\n")
PYEOF
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 · 64 lines · 69 tokens per session scan A e2e677242f26
kernel-pipeline is a skill published in the GitHub repository Pinperepette/context-kernel (24 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 827 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.