self-patch

self-patch is a skill for Claude Code, Codex from jasonkneen/lazar. It costs 93 tokens per session (1,067 once invoked), scanned A, original, MIT.

A process for finding and correcting repeated mistakes made by an agent. It reads the actual code or logs, identifies whether the cause is behavioral, configuration-related, or part of the locked system, then applies or proposes an appropriate fix.

In plain words
What is it for?
Use it to investigate repeated errors, update behavioral rules or configuration when possible, verify the correction, and write a proposal when a protected system change is required.
Why use it?
It turns recurring failures into durable improvements instead of repeating the same apology or workaround.

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/self-patch
Any agent
npx skills add jasonkneen/lazar --skill self-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 self-patch

README.md
[![agentmods](https://agentmods.dev/badge/skills/jasonkneen/lazar/self-patch.svg)](https://agentmods.dev/skills/jasonkneen/lazar/self-patch)
Your own site
<a href="https://agentmods.dev/skills/jasonkneen/lazar/self-patch"><img src="https://agentmods.dev/badge/skills/jasonkneen/lazar/self-patch.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,067 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 $0.00093 $0.01067
Opus 5 $0.00046 $0.00534
Sonnet 5 $0.00019 $0.00213
Haiku 4.5 $0.00009 $0.00107

Measured 4d ago against content hash d3f3ceace396, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-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 4d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (ledger.sh, selftest.sh, stage-proposal.sh), 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.

src/seed-skills/_meta/self-patch/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

self-patch — fixing myself

When I fail the same way twice, I fix it — I don't just apologize. This is the loop. It's REACTIVE (invoked by the operator, or by me noticing mid-session) and TIERED: I fix the non-kernel layers myself and verify; kernel changes I can only PROPOSE (my src/ is locked — that's the safety boundary, not a limitation to route around).

The loop: notice → root-cause → classify → act → record

1. Notice

A repeated mistake, operator feedback ("you did it again"), a failed VERIFY, or a pattern in memory/work-journal.md / bounded logs.

2. Root-cause — read, don't guess

Read the actual code/logs. Confirm the mechanism before fixing. Use gitignore-aware search (bare rg works via .ignore; ls/find for existence). Every good fix I've made came from reading source, not assuming.

3. Classify the layer

  • behavioral — a habit/instruction gap (I stall, I gaslight, I over-write). Fix = a rule in the PINNED hot set.
  • config — an env var, rc file, or ignore file (rg blindness → .ignore; nudge count → LAZAR_STALL_NUDGES). Fix = change the file/var.
  • kernel — needs Rust (max_tokens=8192, reset wipes memory/). I CANNOT edit the locked src/. Fix = draft a proposal (step 4c).

4. Act

4a. Behavioral fix (autonomous). Add ONE tight dated line to the PINNED hot set (see below). Then PROVE it: end my turn with [VERIFY]\ncontains=memory/PINNED.md:<distinctive phrase from the rule>\n[/VERIFY]. Never claim a behavioral fix without a passing VERIFY.

4b. Config fix (autonomous). Change the file/var, then VERIFY the effect (contains=, or a command whose output confirms it). Record it.

4c. Kernel fix (PROPOSAL ONLY — never apply).

  1. staged=$(bash skills/_meta/self-patch/stage-proposal.sh <name>) — stages a writable src/ copy under workspace/proposals//src/.
  2. Delegate the mechanical edit+build to a worker (isolates it from my context) by writing a PRECISE spawn prompt — exact file, exact old→new text, and an EXPECT-VERIFY: block requiring a build-ok marker — then: bash "$LAZAR_HOME/bin/lazar-spawn" <name> <prompt-file>. The worker edits $staged, runs cd $staged && CARGO_TARGET_DIR=/tmp/sp-$$ cargo build --release and, on success, writes $staged/../build-ok + a short DESIGN.md. (Or, for a tiny edit, I do this directly.)
  3. Gate on the envelope (matched:true = it compiled). NEVER run kernel-apply.sh myself.
  4. Surface to the operator, verbatim: "Kernel proposal <name> is staged and verified-building. Review the diff and run bash scripts/kernel-apply.sh <name> to apply."

Read the full file on GitHub · 76 lines

Files

What ships with it

3 files 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. 4d ago First seen · 76 lines · 93 tokens per session scan A d3f3ceace396

Subscribe to this mod's changes

self-patch is a skill published in the GitHub repository jasonkneen/lazar (31 stars, last pushed 22d ago), licensed MIT. It adds 93 tokens to every session and 1,067 once invoked, about $0.0005 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