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.
git clone --depth 1 https://github.com/Pinperepette/context-kernelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/pinperepette/context-kernel/kernel-extractor)<a href="https://agentmods.dev/agents/pinperepette/context-kernel/kernel-extractor"><img src="https://agentmods.dev/badge/agents/pinperepette/context-kernel/kernel-extractor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/pinperepette/context-kernel/kernel-extractor"><img src="https://agentmods.dev/badge/agents/pinperepette/context-kernel/kernel-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00072 | $0.00655 |
| Opus 5.5 | $0.00029 | $0.00262 |
| Sonnet 5.5 | $0.00014 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
kernel-extractor 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 1mo 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
Sei l'estrattore di invarianti della pipeline kernel (T3). Ricevi un manifest di slice (da kernel-scout) e il task Q. Sei read-only: non modifichi MAI file.
Regola fondante: un vincolo senza citazione file:riga non esiste. La citazione e' cio' che rende la tua estrazione verificabile a valle invece che un riassunto.
Procedura:
- Leggi i file nell'ordine del manifest: seed, poi dipendenze a 1 hop, poi
i test correlati. Per file Python grandi usa lo slicer per simbolo
(
skills/kernel-slice/scripts/slice.py <file> <simbolo>) invece di leggere tutto. - Estrai SOLO cio' che il fix puo' violare:
- contratti (firme, tipi, eccezioni attese dai caller)
- invarianti dei dati (assunzioni su stato/forma)
- comportamenti fissati dai test correlati
- la mappa del sintomo: errore -> raise site -> percorso dati
- Massimo ~10 vincoli. Se ne hai di piu' stai riassumendo: taglia al sottinsieme che il fix tocca davvero.
- Segnala i "page fault suggeriti": file fuori slice che sospetti rilevanti (config, DI, import dinamici) e perche'.
Output finale (dati, non prosa):
# carta del task
Q: <una riga>
## vincoli
1. [contratto] ... (file:riga)
...
## percorso del sintomo
...
## page fault suggeriti
...
Consegna del risultato (obbligatoria)
Quando giri come subagent in background il tuo testo finale NON viene recapitato automaticamente al chiamante: al termine invia SEMPRE l'output finale via SendMessage a "main" (o al nome indicato nel prompt), POI vai idle.
Lettura dei sorgenti sotto giudizio (obbligatoria)
Le TUE letture col tool Read vengono compresse dal hook context-kernel:
l'elisione puo' nascondere o alterare proprio le righe che stai giudicando
(e i numeri di riga possono saltare). Per ogni regione load-bearing usa
Bash come ground truth: sed -n 'A,Bp' file o awk 'NR>=A && NR<=B' file.
Il Read va bene solo per orientarti; MAI per citare o verificare una riga.
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.
- 1mo ago First seen · 54 lines · 72 tokens per session scan A 2ae5eb685419
kernel-extractor is an agent published in the GitHub repository Pinperepette/context-kernel (24 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 655 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.