session-judgment-mining SKILL.md skillA
session-judgment-mining from shimo4228/claude-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add shimo4228/claude-harness/session-judgment-mining@git:20261008.b63e5f1Pins git:20261008.b63e5f1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- shimo4228/claude-harness
- Path
skills/session-judgment-mining/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261008.b63e5f1, committed Oct 8, 2026
- First version recorded
- Aug 24, 2026
- Size
- 10,533 bytes
- Repository stars
- 3
- License
- MIT
Mine past Claude Code sessions for the author's recurring judgments and codify them as skills or rules.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# session-judgment-mining — 過去セッション群からの判断・価値観の発掘とスキル化 **Purpose:** ユーザーの判断・価値観は個々のセッションの修正指示（「ここ直して」「こうじゃない」）として発話され、memory に部分的に残るだけで大半は会話履歴に埋まる。このスキルは過去セッション群を遡って発掘し、繰り返された判断を skill として正本化する。learn-eval が「今のセッションから 1 パターン」を抽出するのに対し、これは「過去セッション群の遡及一括発掘」。 --- ## Step 1: 規模把握と全量/サンプリング判定 対象は `ls ~/.claude/projects/$(pwd | tr '/_.' '-')/*.jsonl`（`memory/` サブディレクトリは 対象外）。スラグは `/` だけでなく `_` と `.` も `-` になる — `tr '/' '-'` だけだと存在しない パスを見にいく。 まず**人間発話の turn 数**で読む量を見積もる。ファイルサイズは判断材料にならない — トランスクリプトの 9 割超は tool_result で、33 セッション 89MB でも人間発話は 114KB だった。 - 人間発話が**数百 turn** → 全量パス（サンプリング不要。数十 k tokens で通読できる） - 全量では通読しきれない規模（数千 turn 超が目安）→ サンプリング。フィードバック密度の高いセッション（人間 turn 数上位）を選び、キーワード grep（「直して」「違う」「じゃない？」等）でヒットしたセッションを足す。選んだ範囲と選び方は Step 3 の報告に書く ## Step 2: 人間発話の抽出 Claude / Codex JSONL からの人間発話抽出は `session-theme-mining` helper を使う — 形式差分 （`origin.kind=="human"` / compact 後の `origin` 欠落 / `.message.content` の string・array 両形）と secret redaction の正本が 1 つだからで、自前の抽出器を並置すると片方だけが形式変更に 追随して静かに取りこぼす。 ```bash uv run --directory ~/MyAI_Lab/zenn-content/.claude/skills/session-theme-mining \ python ~/MyAI_Lab/zenn-content/.claude/skills/session-theme-mining/scripts/session_catalog.py \ …
Read the whole file at its exact version.
How to install
mdr add shimo4228/claude-harness/session-judgment-mining@sha256:18cf023f63592e6dThe line at the top of this page pins the label git:20261008.b63e5f1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_okjwyzntfrksxhjo)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Aug 24, 2026 and Oct 8, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261008.b63e5f1 latest | 2026-10-08 | b63e5f1 | 10,533 B | A | view · diff |
| git:20261007.d62d71a | 2026-10-07 | d62d71a | 11,618 B | A | view · diff |
| git:20260925.a3765d2 | 2026-09-25 | a3765d2 | 11,545 B | A | view · diff |
| git:20260919.f95d231 | 2026-09-19 | f95d231 | 11,647 B | A | view · diff |
| git:20260902.9b5c240 | 2026-09-02 | 9b5c240 | 11,169 B | A | view · diff |
| git:20260829.b4cb78e | 2026-08-29 | b4cb78e | 11,189 B | A | view · diff |
| git:20260824.8c93955 | 2026-08-24 | 8c93955 | 11,101 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10533 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
shimo4228/claude-harness · 3 stars · license MIT · pushed 2026-10-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_okjwyzntfrksxhjo GET https://markdownregistry.com/api/v1/resolve?ref=shimo4228/claude-harness/session-judgment-mining GET https://markdownregistry.com/api/v1/blob/18cf023f63592e6d201e2d49d7bab8e26e8a4c458cdf47bdd20b518b7757f99c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.