auto-optimize

A tool for repeatedly testing and improving an existing Claude Code skill. It runs the skill, checks its results against yes-or-no tests, changes the instructions, and keeps useful improvements.

In plain words
What is it for?
Use it to benchmark a skill, diagnose failed evaluations, compare changes over time, and refine its instructions.
Why use it?
It helps find the cases where a skill gives poor results and improve them through repeated testing rather than guesswork.

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/leejuoh/claude-code-zero/auto-optimize
Any agent
npx skills add LeeJuOh/claude-code-zero --skill auto-optimize
Clone the repo
git clone --depth 1 https://github.com/LeeJuOh/claude-code-zero

Made for: Claude Code, Codex.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,273 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 $0.00065 $0.04273
Opus 5 $0.00032 $0.02136
Sonnet 5 $0.00013 $0.00855
Haiku 4.5 $0.00006 $0.00427

Measured 2d ago against content hash a530ce92e6d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-optimize 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.

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.

plugins/skill-creator-pro/skills/auto-optimize/SKILL.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch for Skills

Bundled with skill-creator-pro. This skill reads design guidance from its sibling via ${CLAUDE_SKILL_DIR}/../skill-creator-pro/. The two skills ship together in the skill-creator-pro plugin and cannot be installed separately.

Most skills work about 70% of the time. The other 30% you get garbage. The fix isn't to rewrite the skill from scratch. It's to let an agent run it dozens of times, score every output, and tighten the prompt until that 30% disappears.

This skill adapts Andrej Karpathy's autoresearch methodology to Claude Code skills, enhanced with:

  • Reflection-driven mutation -- reads failed outputs to diagnose WHY they failed, then proposes targeted fixes. The difference between throwing darts blindfolded and throwing them with your eyes open.
  • Per-eval tracking -- tracks each eval separately so improving one at another's expense gets caught.
  • Structured archive -- session-surviving changelog that new sessions read to avoid repeating failed experiments.
  • Stuck detection -- recognizes when incremental mutations hit a wall and escalates strategy.

The Core Job

Take any existing skill, define what "good output" looks like as binary yes/no checks, then run an autonomous loop that:

  1. Generates outputs from the skill using test inputs
  2. Scores every output against the eval criteria
  3. Reflects on failed outputs -- reads the actual failures and diagnoses the root cause
  4. Mutates the skill prompt to fix the diagnosed issue
  5. Keeps mutations that improve the score, discards the rest
  6. Repeats until the score ceiling is hit or the user stops it

Output: An improved SKILL.md + results.json log + structured changelog.md + a live HTML dashboard.


Before Starting: Gather Context

STOP. Do not run any experiments until the fields below are confirmed with the user. Ask for any missing fields before proceeding.

  1. Target skill -- Which skill to optimize? (exact path to SKILL.md)
  2. Test inputs -- 3-5 different prompts/scenarios to test with. Variety matters -- pick inputs that cover different use cases so we don't overfit to one scenario.
  3. Runs per experiment -- How many times to run the skill per mutation? Default: 5. More runs = more reliable scores but slower. 5 is the sweet spot.
  4. Budget cap -- Optional. Max number of experiment cycles before stopping. Default: no cap (runs until you stop it).

Read the full file on GitHub · 381 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 · 381 lines · 65 tokens per session scan A a530ce92e6d4

Subscribe to this mod's changes

auto-optimize is a skill published in the GitHub repository LeeJuOh/claude-code-zero (51 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 4,273 once invoked, about $0.0003 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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens