self-improve-log

self-improve-log is a skill for Claude Code from Feynman520/d06-p01-self-improve. It costs 46 tokens per session (527 once invoked), scanned A, original, MIT.

A skill for manually recording one improvement lesson from the current conversation. A skill is a set of instructions that tells the coding agent how to handle a particular task.

In plain words
What is it for?
Recording the problem, desired result, category, possible fixes, project details, and an anonymized lesson, then optionally suggesting or applying a fix.
Why use it?
It provides a defined way to capture a useful, repeatable lesson when the agent’s result did not match what the user wanted.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the self-improve plugin — 1 skill, 1 MCP server shipped together

Good fit Recording the problem, desired result, category, possible fixes, project details, and an anonymized lesson, then optionally suggesting or applying a fix.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/feynman520/d06-p01-self-improve/self-improve-log
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.

Any agent
npx skills add Feynman520/d06-p01-self-improve --skill self-improve-log
Clone the repo
git clone --depth 1 https://github.com/Feynman520/d06-p01-self-improve

Made for: Claude Code.

Or install self-improve, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 self-improve-log

README.md
[![agentmods](https://agentmods.dev/badge/skills/feynman520/d06-p01-self-improve/self-improve-log/github.svg)](https://agentmods.dev/skills/feynman520/d06-p01-self-improve/self-improve-log)
Your own site
<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.

agentmods 80×15 button for self-improve-log

Your own site · 80×15
<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>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 527 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00046 $0.00527
Opus 5 $0.00023 $0.00264
Sonnet 5 $0.00009 $0.00105
Haiku 4.5 $0.00005 $0.00053

Measured 2d ago against content hash b59046c12176, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 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.

skills/self-improve-log/SKILL.md · 19 lines

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

  1. 대상 특정 — 사용자가 인자로 지목했으면 그것을, 아니면 직전 대화에서 "결과가 사용자 의도와 어긋났던 순간"을 찾는다. 못 찾으면 무엇을 기록할지 한 번만 묻는다.
  2. 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.
  3. 분류 선택 (5종 고정): 오해 요구를 잘못 이해 / 지식 부족 사용자·환경 고유 사실을 몰랐음 / 도구 실패 도구·명령 실패 / 환경 문제 설정·경로·권한 / 반복 비효율 같은 수작업 반복(자동화 후보)
  4. log 호출category, lesson(일반화된 한 문장, 필수), what_happened, user_wanted, solution_candidates, project(현재 작업 폴더 절대경로), agent(claude|codex).
  5. 한 줄 알림📝 개선점 기록: "<lesson>" (<category>).
  6. 자동 적용 — 반환값에 ripe가 있으면 그 기록들이 같은 교훈인지 확인한 뒤 apply_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.
  7. 사용자가 "기록하지 마"라고 하면 저장된 기록 파일을 즉시 삭제한다.
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 Changed · -5 lines b59046c12176
  2. 9d ago First seen · 24 lines · 46 tokens per session scan A 1925ebb2f7f9

Subscribe to this mod's changes

self-improve-log is a skill published in the GitHub repository Feynman520/d06-p01-self-improve (0 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 527 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

memem-mine

Opt in to memem's event-triggered mining. New sessions are mined automatically via the Stop hook.

TT-Wang/memem · 26 tokens

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…

0xmariowu/Autosearch · 89 tokens

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.

0xmariowu/Autosearch · 69 tokens

stats

Show Captain Memo's corpus statistics (chunks per channel, observation counts, indexing progress, embedder info). Use when the user types /captain-memo:stats.

kalinbogatzevski/captain-memo · 36 tokens

observations

List recent captured session observations (the Haiku-summarized voyage logs). Use when the user wants to see what Captain Memo has logged from past sessions.

kalinbogatzevski/captain-memo · 34 tokens

claude-bridge-role-memory-keeper

Playbook for a Claude Code agent in the dedicated memory keeper role — single-writer for shared agent memory across a team of 3+ peers. Use when you are designated as the keeper (= other peers send you write candidates, you write them and watch for drift). Memory hygiene + reconciliation against the canon + drift…

michalekz/claude-bridge · 102 tokens