skill-evolve

skill-evolve is a skill for Claude Code from LeeYudok/agents-scaffold. It costs 51 tokens per session (601 once invoked), scanned A, original, MIT.

A review process for improving an agent skill after it produces a mistake, omission, or useful new warning. It reads the skill, proposes a focused change, asks for approval, and then tests the improvement.

In plain words
What is it for?
Use it after running a skill when you have feedback or discovered a trap. It can update the skill’s steps or warnings, show the proposed difference, and verify the change with a small evaluation.
Why use it?
A skill can repeat the same failure if the lesson is not added to its instructions. This process preserves warnings and checks that the proposed fix addresses the original problem.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

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/leeyudok/agents-scaffold/skill-evolve
Any agent
npx skills add LeeYudok/agents-scaffold --skill skill-evolve
Clone the repo
git clone --depth 1 https://github.com/LeeYudok/agents-scaffold

Made for: Claude Code.

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 skill-evolve

README.md
[![agentmods](https://agentmods.dev/badge/skills/leeyudok/agents-scaffold/skill-evolve.svg)](https://agentmods.dev/skills/leeyudok/agents-scaffold/skill-evolve)
Your own site
<a href="https://agentmods.dev/skills/leeyudok/agents-scaffold/skill-evolve"><img src="https://agentmods.dev/badge/skills/leeyudok/agents-scaffold/skill-evolve.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 601 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 5.1 $0.00051 $0.00601
Opus 5 $0.00026 $0.00300
Sonnet 5 $0.00010 $0.00120
Haiku 4.5 $0.00005 $0.00060

Measured 6d ago against content hash 486367f1f143, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-evolve 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 6d 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.

.claude/skills/skill-evolve/SKILL.md · 60 lines

What it actually says

스킬 자기개선

원형: leeyudok/doksam-skills 의 동명 스킬. 템플릿 동봉용으로 의도적 분기 — 자동 동기하지 않으며, 좋은 개선은 수동 체리픽.

실행 중 발견한 문제, 사용자 피드백을 해당 스킬의 SKILL.md에 반영한다.

트리거

/skill-evolve <스킬명> <피드백>

프로세스

  1. 대상 읽기: .claude/skills/<스킬명>/SKILL.md 전체 읽기.
  2. 분석: 피드백 + 최근 실행 맥락 분석 → 변경 부분 결정.
    • 새로운 gotcha → ## Learned warnings 섹션에 날짜와 함께 추가
    • 단계 수정 → 프로세스 섹션 업데이트
    • 잘못된 명령 → 수정
  3. 제안: 기존 내용 인용 + 변경 diff(추가/삭제 라인별) 제시.
  4. 확인 요청: "적용하시겠습니까? (Y/n)"
  5. 적용: 확인 후 SKILL.md 직접 수정.
  6. 커밋: 브랜치 재확인 후:
    git add .claude/skills/<스킬명>/SKILL.md
    git commit -m "evolve skill/<스킬명>: <요약>"
    
  7. 검증(미니 eval): 개선 계기가 된 것과 같은 유형의 입력으로 수정된 스킬을 실행해, 개선 전 실패했던 지점이 실제로 고쳐졌는지 전후 비교로 확인.

규칙

  • 기존 Learned warnings는 삭제하지 않고 누적
  • 날짜 태그 필수: (YYYY-MM-DD)
  • 중복 경고는 병합
  • 커밋 직전 브랜치 재확인 (main 위 커밋 방지)

출력 형식

개선 제안
기존: [인용]
제안: [수정안]

diff:
+ 추가 라인
- 삭제 라인

적용하시겠습니까? (Y/n)

Learned warnings

(실행 중 발견한 주의사항이 여기에 누적됩니다)

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. 6d ago First seen · 60 lines · 51 tokens per session scan A 486367f1f143

Subscribe to this mod's changes

skill-evolve is a skill published in the GitHub repository LeeYudok/agents-scaffold (25 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 601 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.