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 skills add Feynman520/d06-p01-self-improve --skill self-improve-loggit clone --depth 1 https://github.com/Feynman520/d06-p01-self-improveWrote 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.
[](https://agentmods.dev/skills/feynman520/d06-p01-self-improve/self-improve-log)<a href="https://agentmods.dev/skills/feynman520/d06-p01-self-improve/self-improve-log"><img src="https://agentmods.dev/badge/skills/feynman520/d06-p01-self-improve/self-improve-log/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.
<a href="https://agentmods.dev/skills/feynman520/d06-p01-self-improve/self-improve-log"><img src="https://agentmods.dev/badge/skills/feynman520/d06-p01-self-improve/self-improve-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00527 |
| Opus 5.5 | $0.00018 | $0.00211 |
| Sonnet 5.5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
self-improve-log 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 1mo 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.
What it actually says
self-improve-log — 수동 즉시 기록
방금 대화에서 드러난 개선점 1건을 self-improve MCP의 log 도구로 기록한다. 자동 감지가 놓친 것을 사용자가 직접 지목하는 통로다.
절차
- 대상 특정 — 사용자가 인자로 지목했으면 그것을, 아니면 직전 대화에서 "결과가 사용자 의도와 어긋났던 순간"을 찾는다. 못 찾으면 무엇을 기록할지 한 번만 묻는다.
- 한 문장 테스트 — 다음에도 써먹을 교훈을 한 문장으로 쓸 수 있는가? 못 쓰면(새 요구 추가·일회성 취향 조정 등) 기록 대상이 아니라고 답하고 중단한다.
- 분류 선택 (5종 고정):
오해요구를 잘못 이해 /지식 부족사용자·환경 고유 사실을 몰랐음 /도구 실패도구·명령 실패 /환경 문제설정·경로·권한 /반복 비효율같은 수작업 반복(자동화 후보) log호출 —category,lesson(일반화된 한 문장, 필수),what_happened,user_wanted,solution_candidates,project(현재 작업 폴더 절대경로),agent(claude|codex).- 한 줄 알림 —
📝 개선점 기록: "<lesson>" (<category>). - 자동 적용 — 반환값에
ripe가 있으면 그 기록들이 같은 교훈인지 확인한 뒤apply_rule로 규칙을 적용하고📌 규칙 자동 적용: [R-nnn] …한 줄을 출력한다.existing_artifact가 있으면 새로 만들지 말고 그 산출물을 고친다.recurrence_of_resolved가 있으면 더 강한 처방(스킬·스크립트)을 검토한다. - 사용자가 "기록하지 마"라고 하면 저장된 기록 파일을 즉시 삭제한다.
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.
- 1mo ago Changed · -5 lines b59046c12176
- 2mo ago First seen · 24 lines · 46 tokens per session scan A 1925ebb2f7f9
self-improve-log is a skill published in the GitHub repository Feynman520/d06-p01-self-improve (0 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 527 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
autosearch:context-retention-policy
Session-level policy for keeping the runtime AI's context window healthy across long research — keep-last-k tool results, offload older evidence to disk, trigger compaction at thresholds. Borrows MiroThinker's keeptoolresult, deepagents' summarization middleware, and deer-flow's SummarizationEvent pattern. Orthogonal…
autosearch:experience-compact
Promote recurring patterns from experience/patterns.jsonl into the compact experience.md digest (≤120 lines, read by runtime AI before calling the skill). Triggers on N-events / file-size / user-feedback / session-end. Guards against single-success noise and pollution via promotion thresholds.
quarry-capture
Persist something worth keeping into quarry so it survives context compaction and is findable by quarry-recall later — a durable fact, a distilled lesson, or a URL to index. Trigger phrases: "remember this", "save this fact", "note that we decided X", "learn this lesson", "the rule going forward is X", "ingest this…
quarry-recall
Retrieve what quarry already knows before researching from scratch or guessing. Covers three overlapping intents, one tool: understand code ("how does X work", "where is X defined", "what calls X"); recall project knowledge or a decision ("what did we decide about X", "why is it this way", "did we consider Y…
stats
Show Captain Memo's corpus statistics (chunks per channel, observation counts, indexing progress, embedder info). Use when the user types /captain-memo:stats.
doctor
Health probe across the worker, embedder, summarizer, queue, vector index, schema, cross-AI wiring and plugin install (cache and live versions). Use when the user types /captain-memo:doctor or when something seems wrong.