propose-kernel-patch

propose-kernel-patch is a skill for Claude Code, Codex from jasonkneen/lazar. It costs 0 tokens per session (744 once invoked), scanned A, original, MIT.

A procedure for proposing changes to Lazar's protected kernel files, such as its command runner or source code. The proposal is placed in a workspace for the user to review and apply.

In plain words
What is it for?
Use it when a bug or feature requires changing the kernel, its command-line options, event records, or built-in skills. It is not for behavior that belongs in a regular skill.
Why use it?
The protected files cannot be edited directly by ordinary skills, so this creates a complete, reviewable change instead of a partial or blocked edit.

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/jasonkneen/lazar/propose-kernel-patch
Any agent
npx skills add jasonkneen/lazar --skill propose-kernel-patch
Clone the repo
git clone --depth 1 https://github.com/jasonkneen/lazar

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for propose-kernel-patch

README.md
[![agentmods](https://agentmods.dev/badge/skills/jasonkneen/lazar/propose-kernel-patch.svg)](https://agentmods.dev/skills/jasonkneen/lazar/propose-kernel-patch)
Your own site
<a href="https://agentmods.dev/skills/jasonkneen/lazar/propose-kernel-patch"><img src="https://agentmods.dev/badge/skills/jasonkneen/lazar/propose-kernel-patch.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 744 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 $0.00000 $0.00744
Opus 5 $0.00000 $0.00372
Sonnet 5 $0.00000 $0.00149
Haiku 4.5 $0.00000 $0.00074

Measured 3d ago against content hash e76d9b8c0a74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

propose-kernel-patch 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 3d 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.

src/seed-skills/_meta/propose-kernel-patch/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

propose-kernel-patch

When you identify a change that needs to happen in the immutable kernel (bin/lazar or src/), you cannot apply it yourself — sandbox-exec blocks writes there, and chflags uchg blocks them at the OS level too. Instead, stage a complete proposal in workspace/ that the user can review and apply with one command.

When to use

  • You found a bug in the kernel (e.g. error path doesn't emit structured output, missing flag, incorrect timeout).
  • You need a new kernel feature (e.g. a new CLI flag, a new event type in the stream).
  • You want to update a seed skill (those are baked into the binary at compile time).
  • You can articulate the patch precisely and it's small enough to review.

Do NOT use this for things that should be skills. The kernel does ONE thing — runs bash + records events. Adding behavior to skills is always preferred.

How to use

  1. Pick a short kebab-case slug for the proposal (e.g. http-error-emit, add-resume-flag).

  2. Create the proposal directory:

    mkdir -p $LAZAR_HOME/workspace/proposals/<slug>/src/src
    mkdir -p $LAZAR_HOME/workspace/proposals/<slug>/src/seed-skills
    
  3. Copy the FULL current kernel as the starting point:

    cp -R $LAZAR_HOME/src/. $LAZAR_HOME/workspace/proposals/<slug>/src/
    
  4. Apply your changes inside $LAZAR_HOME/workspace/proposals/<slug>/src/:

    # edit src/src/main.rs, src/sandbox.sb, src/seed-skills/<...> as needed
    
  5. Write a README explaining what changed and why:

    cat > $LAZAR_HOME/workspace/proposals/<slug>/README.md <<'EOF'
    # <slug>
    
    ## Summary
    <one paragraph: what the change does>
    
    ## Why
    <observed problem or new capability needed>
    
    ## Files changed
    - src/src/main.rs (lines ~X-Y): <what>
    - src/seed-skills/...: <what>
    
    ## Risk
    <what could break, what to test after applying>
    EOF
    
  6. Tell the user:

    I've staged a kernel patch at $LAZAR_HOME/workspace/proposals/<slug>/.
    Review with: diff -u --recursive $LAZAR_HOME/src $LAZAR_HOME/workspace/proposals/<slug>/src
    Apply with:  bash $LAZAR_HOME/scripts/kernel-apply.sh <slug>
    

Read the full file on GitHub · 67 lines

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. 3d ago First seen · 67 lines · 0 tokens per session scan A e76d9b8c0a74

Subscribe to this mod's changes

propose-kernel-patch is a skill published in the GitHub repository jasonkneen/lazar (31 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 744 tokens. 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