What is skill-evolution?

A plugin that records whether agent skills succeed or fail and uses failure traces to suggest improvements to their instruction files. A plugin is an add-on that extends an agent's available behavior.

Use it to collect skill outcomes and support evidence-based revisions of skill instructions.

It helps maintain skills using measured results from real use rather than leaving their instructions unchanged as problems appear.

skill-evolution — Plugin by okdk7788

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.

Claude Code

/plugin marketplace add okdk7788/skill-evolution

agentmods

npx agentmods add plugins/okdk7788/skill-evolution/marketplace

Clone the repo

git clone --depth 1 https://github.com/okdk7788/skill-evolution

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

skill-evolution 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 yesterday.

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-plugin/marketplace.json · 23 lines

What it actually says

{
  "name": "skill-evolution",
  "owner": {
    "name": "local"
  },
  "metadata": {
    "description": "Companion to self-improving-skills: adds Hermes GEPA-style measured evolution — success/failure outcome telemetry + reflective skill optimization."
  },
  "plugins": [
    {
      "name": "skill-evolution",
      "source": "./plugins/skill-evolution",
      "description": "학습 스킬의 성공/실패 outcome을 수집하고, 실패 트레이스 기반으로 SKILL.md를 반영·변이·평가·선별해 진화시킨다 (Hermes self-evolution의 측정 기반 최적화 축).",
      "version": "0.1.0",
      "author": {
        "name": "local"
      },
      "license": "MIT",
      "category": "development"
    }
  ]
}

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.

yesterday First seen · 23 lines scan A 62a7e13b5f1c

Subscribe to this mod's changes

skill-evolution is a plugin published in the GitHub repository okdk7788/skill-evolution (2 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.

agent-skills claude-code claude-code-plugin gepa hermes-agent self-improvement

skill-evolution

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

opendirectory-marketplace

paleo

unknowns

unknowns

robcsaszar-retrospective

retrospective