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 shimo4228/claude-harness --skill wiki-harvestgit clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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/shimo4228/claude-harness/wiki-harvest)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/wiki-harvest"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/wiki-harvest/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/shimo4228/claude-harness/wiki-harvest"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/wiki-harvest.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 | $0.00177 | $0.05531 |
| Opus 5 | $0.00088 | $0.02766 |
| Sonnet 5 | $0.00035 | $0.01106 |
| Haiku 4.5 | $0.00018 | $0.00553 |
Grade A, and why
wiki-harvest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-harvest — LLM wiki から研究 repo への還元
研究 repo セッションで実行し、LLM wiki（Obsidian Vault）の合成知識から その repo の次アクションを変えうる候補だけを抽出して、一次出典付きのランク付き候補台帳（ledger）を repo 内に生成する。
各研究 repo の CLAUDE.md「Research Wiki Consultation」節に passive prose で書かれている還元マップ（4カテゴリ）を、再現可能な能動手続きに形式化したもの。wiki の合成知識を diff → ランク付き候補 → repo 内 ledger に落とす。daily-research → wiki（合成層）→ repo（昇格）という一方向ループの最終辺を1コマンドで回す。
兄弟スキル:
wiki-query= chat 上の自由 Q&A（良回答はwiki/concept/へ書き戻す read-write）。wiki-harvest= repo 向け定型抽出 → 台帳で、wiki には書き込まない。置き換えではない。
Vault パス（固定）
VAULT="$HOME/Library/Mobile Documents/iCloud~md~obsidian/Documents/Obsidian Vault"
- 概念ページ:
$VAULT/wiki/concept/<概念名>.md - インデックス:
$VAULT/wiki/index.md - 構造グラフ:
$VAULT/wiki/graph.jsonld（symlink →~/MyAI_Lab/daily-research/graph.jsonld） - 原資料:
$VAULT/daily-research/
この skill は shimo4228 の個人運用（固定 vault + 自分の研究 repo 群）に紐づく。repo→concept マッピングは skill にハードコードせず、各 repo の CLAUDE.md から読む（下記 Step 1）。
制約
- wiki は read-only。この skill から vault 内のいかなるファイルにも書き込まない。wiki の更新（ingest / index / log）は vault セッションの
/ingestの領域。一方向ループ（source → wiki → repo）を保全する。 - 書き込みは repo 内の ledger のみ。
.notes/wiki-harvest/ledger.md（working/non-citable・gitignore 対象）だけを生成・更新する。 - durable/citable な成果物（
docs/adr//graph.jsonld/glossary.md/manifesto.md）には書かない。それらへの昇格は人間承認の別ステップ（reversibility gate + 既存ルール「promotion は repo author が判断」）。 - prototype 系候補（
response-type: prototype）のコード・計器も自動で実装しない。この skill は候補の抽出と triage までで、計器/spike の実行は人間承認の別ステップ。harvest がやるのは「何を測るべきか」を ledger に書くところまで。 - iCloud dataless プレースホルダに注意: 読んだ concept ページ本文が空なら未ダウンロードの可能性。その旨を報告する。
手順
Step 1 — repo と対象 concept の特定
- cwd / git remote から現在の研究 repo を判定（
agent-knowledge-cycle/agent-attribution-practice/contemplative-agent/authorship-strategy等）。 - その repo の
CLAUDE.md内「Research Wiki Consultation」節を Read し、主担当ページ+隣接に挙がっている concept 名を取得する。マッピングはここ（repo 側）が正本。skill にハードコードしない。 - 節が無い repo は fallback（節を持つ repo のほうが少ない — 実測 2026-08-23 では
agent-attribution-practice と authorship-strategy のみ。repo 名の列挙はすぐ腐るので
grep 'Research Wiki Consultation' <repo>/CLAUDE.mdで毎回確かめる）:$VAULT/wiki/graph.jsonldのtrack値（akc / aap / contemplative / authorship）と repo 名から対象 concept を推定し、「consultation 節が欠落している」ことを報告する（後で節を backfill すべき signal）。
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.
- 7d ago Changed 49ad51b7c272
- 12d ago First seen · 197 lines · 177 tokens per session scan A be0ca54a6da7
wiki-harvest is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 6d ago), licensed MIT. It adds 177 tokens to every session and 5,531 once invoked, about $0.0009 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 skills, from other repositories
agent-adoption-triage
Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…
job-description-skill
A job-description analysis skill that turns a vacancy listing and a candidate’s background into an HTML report about fit, gaps, interview topics, and application strategy.
offer-compare-skill
A decision assistant for comparing two or more job offers across pay, growth, company strength, team risk, promotion, AI exposure, and lifestyle. Total compensation means the combined value of salary, bonuses, shares, and sign-on payments.
offer-toolkit-skill
A set of job-search tools covering the path from finding a vacancy to accepting an offer. It includes separate tools for job searches, job-description analysis, tailored resumes, behavioral interviews, offer comparisons, and salary negotiation.
bq-skill
A coaching workflow for building a reusable library of truthful stories for behavioral job interviews. It uses structures such as STAR—Situation, Task, Action, Result—and can connect stories to a job description and résumé.
linkedin-job-search-skill
A job-search assistant that uses a sample job description and your resume to find and rank similar public LinkedIn Jobs listings. LinkedIn Jobs is LinkedIn’s section for advertised employment positions.