kernel-repo-slice

A repository-slicing tool that selects the files most likely to affect a specific bug or error in a large codebase.

In plain words
What is it for?
Use it with a stack trace, error message, or suspected file paths to produce an ordered file manifest, including related importers and callers.
Why use it?
It narrows the working set before code exploration, reducing irrelevant reading while keeping excluded files recoverable if needed. A repository is a project's complete collection of source files and related files.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/pinperepette/context-kernel/kernel-repo-slice
Any agent
npx skills add Pinperepette/context-kernel --skill kernel-repo-slice
Clone the repo
git clone --depth 1 https://github.com/Pinperepette/context-kernel

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,019 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00084 $0.01019
Opus 5 $0.00042 $0.00509
Sonnet 5 $0.00017 $0.00204
Haiku 4.5 $0.00008 $0.00102

Measured 2d ago against content hash 42fe98a3d1cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kernel-repo-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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/repo_slice.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

claude-context-kernel/skills/kernel-repo-slice/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kernel-repo-slice — working set del repo indotto dal bug

Dato un task Q (il bug), calcola C' = P_Q(C): la proiezione del repository sul sottinsieme di file che puo' influenzare il sintomo.

Quando usarla

  • Bug con stack trace / messaggio d'errore in un repo medio-grande.
  • PRIMA di grep esplorativi a tappeto: la slice guida l'esplorazione.
  • NON serve su repo piccoli (< ~50 file): leggi e basta.

Procedura

  1. Raccogli il sintomo piu' concreto disponibile: stack trace intero > messaggio d'errore quotato > path indiziati > descrizione vaga.
  2. Esegui lo slicer deterministico:
  • Pi: chiama il tool nativo kernel_repo_slice; se budget manca viene derivato dalla finestra di contesto viva.
  • Claude Code:
python3 ${CLAUDE_PLUGIN_ROOT}/skills/kernel-repo-slice/scripts/repo_slice.py <repo_root> \
    --symptom "$(cat /percorso/sintomo.txt)"        # o --symptom "testo"
# opzioni: --seed <file> (aggiunge seed espliciti), --importers-depth N,
#          --max-files N, --json, --anchor-ends (seed in testa e
#          importatori/caller in coda contro il lost-in-the-middle; solo
#          ordine, mai selezione)

Negli altri harness risolvi scripts/repo_slice.py relativamente alla directory di questa skill.

  1. Leggi il manifest: seed (con provenienza), file per rilevanza (dipendenza/importatore/test + hop), conteggio esclusi.
  2. Lavora DALLA slice: leggi prima i seed, poi le dipendenze a 1 hop, i test correlati sono il riproduttore.

Budget (operatore costo)

La risorsa vera e' la FINESTRA DI CONTESTO: --budget N e' in TOKEN stimati (size/4) che il working set costera' quando i file verranno letti — 10 file enormi costano piu' di 100 piccoli. Lo script sceglie DA SOLO la chiusura piu' ricca che rientra nel vincolo (scala misurata col bench di sufficienza: regge a ogni gradino). Ordini di grandezza: 30k token ~ working set generoso, 10k ~ stretto. Se nemmeno il minimo (seed + test correlati) rientra, scende DA SOLO a granularita' di SIMBOLO (T2b): dai frame del traceback ricava il simbolo top-level che racchiude ogni riga — e se e' un metodo di classe, solo le righe del metodo — e il manifest guadagna la sezione ## T2b con etichette, costo e COMANDI DI ESTRAZIONE pronti (sed per i metodi, slice.py per le funzioni top-level). Leggi le slice coi comandi, non i file interi; page fault = risali al file solo se la slice non basta. Misurato su pandas: minimo file-level ~372k token -> T2b ~15k (-96%). Il manifest riporta config scelta e costo nella riga budget:. Controllo manuale: --deps-depth e --importers-depth.

Read the full file on GitHub · 74 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 74 lines · 84 tokens per session scan A 42fe98a3d1cc

Subscribe to this mod's changes

kernel-repo-slice is a skill published in the GitHub repository Pinperepette/context-kernel (24 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,019 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens