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.
npx agentmods add commands/okdk7788/skill-evolution/evolution-statusgit clone --depth 1 https://github.com/okdk7788/skill-evolutionWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.00291 |
| Opus 5 | $0.00012 | $0.00146 |
| Sonnet 5 | $0.00005 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
evolution-status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
학습 스킬들의 진화 상태 — 사용 빈도 대비 실패율로 어떤 스킬을 다듬을 가치가 큰지 보여줍니다.
다음을 실행하고 결과를 사용자에게 그대로 보여주세요:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/evolution_report.py"
읽는 법:
use— self-improving-skills 텔레메트리 기준 사용 횟수.ok/fail— skill-evolution이 Stop 훅에서 수집한 성공/실패 outcome.fail%— 실패율.priority— 사용량 가중 × 스무딩된 실패율(높을수록 최적화 우선).*opt— 이미/optimize-skill로 최적화된 적 있는 스킬.
1순위 후보가 있으면 사용자에게 /optimize-skill <name> 실행을 제안하세요. outcome이 아직 없으면(신선한 설치) "스킬이 실제로 쓰이면서 Stop 훅이 돌면 데이터가 쌓인다"고 안내하세요.
$ARGUMENTS 에 json 이 오면 evolution_report.py json 으로 원본 데이터를 보여주세요.
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 · 21 lines · 23 tokens per session scan A 1de0dbcbfeed
evolution-status is a command published in the GitHub repository okdk7788/skill-evolution (1 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 291 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 2026-08-31.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
dashboard
Open the claude-smart dashboard (http://localhost:3001) in the browser, starting the backend and dashboard if they aren't running.
remember
Save text as a project memory in Rembric.
greater-invisibility
/volumes/vixinssd/wizardsoftheghosts/generated/openclaw/greater-invisibility/SKILL.md.
animal-friendship
/volumes/vixinssd/wizardsoftheghosts/generated/openclaw/animal-friendship/SKILL.md.
animal-handling
/volumes/vixinssd/wizardsoftheghosts/generated/openclaw/animal-handling/SKILL.md.