self-improve

self-improve is a skill for Claude Code from Yeachan-Heo/oh-my-claudecode. It costs 13 tokens per session (5,163 once invoked), scanned A, original, MIT.

An automated system for repeatedly improving code by researching changes, planning them, testing different implementations, and keeping a history of the results.

In plain words
What is it for?
Use it to run iterative code-improvement experiments, compare proposed changes, record outcomes, and stop when its configured conditions are met.
Why use it?
It removes the need to coordinate each improvement attempt manually and can continue through failed plans or individual agent errors.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the oh-my-claudecode plugin — 39 skills, 21 commands, 19 agents, 11 hooks, 1 MCP server shipped together

Good fit Use it to run iterative code-improvement experiments, compare proposed changes, record outcomes, and stop when its configured conditions are met.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yeachan-heo/oh-my-claudecode/self-improve
About the project

Oh My Claude Code is a multi-agent orchestration system for Claude Code, coordinating specialized agents, commands, skills, hooks, and workflows. It is designed for developers who want Claude Code to handle coding tasks through coordinated agent roles. Catalogue entries are components of its Claude Code workflow, including agents, commands, skills, hooks, instructions, MCP configuration, and a plugin.

Yeachan-Heo/oh-my-claudecode · 39,107 stars · on GitHub · oh-my-claudecode.dev

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.

Any agent
npx skills add Yeachan-Heo/oh-my-claudecode --skill self-improve
Clone the repo
git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode

Made for: Claude Code.

Or install oh-my-claudecode, the plugin that ships this one along with the rest of its 39 skills, 21 commands, 19 agents, 11 hooks, 1 MCP server.

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-improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/yeachan-heo/oh-my-claudecode/self-improve/github.svg)](https://agentmods.dev/skills/yeachan-heo/oh-my-claudecode/self-improve)
Your own site
<a href="https://agentmods.dev/skills/yeachan-heo/oh-my-claudecode/self-improve"><img src="https://agentmods.dev/badge/skills/yeachan-heo/oh-my-claudecode/self-improve/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.

agentmods 80×15 button for self-improve

Your own site · 80×15
<a href="https://agentmods.dev/skills/yeachan-heo/oh-my-claudecode/self-improve"><img src="https://agentmods.dev/badge/skills/yeachan-heo/oh-my-claudecode/self-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 21 Apr 2026
  • Snyk warn 21 Apr 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Privilege Escalation · line 24
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
How audits are shown
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 5.1 $0.00013 $0.05163
Opus 5 $0.00006 $0.02582
Sonnet 5 $0.00003 $0.01033
Haiku 4.5 $0.00001 $0.00516

Measured 9d ago against content hash 262acfd257d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

self-improve 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/plot_progress.py, scripts/resolve-paths.mjs, scripts/validate.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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

skills/self-improve/SKILL.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Improvement Orchestrator

You are the loop controller for the self-improvement system. You manage the full lifecycle: setup, research, planning, execution, tournament selection, history recording, visualization, and stop-condition evaluation. You delegate to specialized OMC agents and coordinate their inputs and outputs.


Autonomous Execution Policy

NEVER stop or pause to ask the user during the improvement loop. Once the gate check passes and the loop begins, you run fully autonomously until a stop condition is met.

  • Do not ask for confirmation between iterations or between steps within an iteration.
  • Do not summarize and wait — execute the next step immediately.
  • On agent failure: retry once, then skip that agent and continue with remaining agents. Log the failure in iteration history.
  • On all plans rejected: log it, continue to the next iteration automatically.
  • On all executors failing: log it, continue to the next iteration automatically.
  • On benchmark errors: log the error, mark the executor as failed, continue with other executors.
  • The only things that stop the loop are the stop conditions in Step 11.
  • Trust boundary: The loop runs benchmark commands as-is inside the target repo. The user explicitly confirms the repo path and benchmark command during setup. The loop does NOT install packages, modify system config, or access network resources beyond what the benchmark command does.
  • Sealed files: validate.sh enforces that benchmark code cannot be modified by the loop, preventing self-modification of the evaluation.

State Tracking

Self-improve artifacts live under a resolved root returned by scripts/resolve-paths.mjs.

  • New runs default to .omc/self-improve/topics/default/.
  • When the user provides a topic or slug, use .omc/self-improve/topics/{topic_slug}/.
  • Legacy single-track state at .omc/self-improve/ remains valid only as a compatibility fallback when no explicit topic/slug is supplied and that flat layout already exists.

Read the full file on GitHub · 399 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. 9d ago First seen · 399 lines · 13 tokens per session scan A 262acfd257d8

Subscribe to this mod's changes

self-improve is a skill published in the GitHub repository Yeachan-Heo/oh-my-claudecode (39,107 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 5,163 once invoked, about $0.0001 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 2026-09-03.