source-extract

source-extract is a skill for Claude Code, Codex from ozzy-labs/suasor. It costs 117 tokens per session (755 once invoked), scanned A, a copy of meeting-followup, MIT.

A procedure for turning a document into suggested tasks, decisions, or draft replies using Suasor, a document and knowledge-management system. It requires a person to review and approve suggestions before they are saved.

In plain words
What is it for?
Use it to extract follow-up tasks, recorded decisions, or reply drafts from a specific document. It is suited to workflows where a human must approve each proposed item.
Why use it?
It prevents unreviewed extraction results from being added automatically to stored records. It also provides a defined process for finding the source, generating candidates, and accepting or rejecting them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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.

agentmods
npx agentmods add skills/ozzy-labs/suasor/source-extract
Any agent
npx skills add ozzy-labs/suasor --skill source-extract
Clone the repo
git clone --depth 1 https://github.com/ozzy-labs/suasor

Made for: Claude Code, Codex.

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 source-extract

README.md
[![agentmods](https://agentmods.dev/badge/skills/ozzy-labs/suasor/source-extract.svg)](https://agentmods.dev/skills/ozzy-labs/suasor/source-extract)
Your own site
<a href="https://agentmods.dev/skills/ozzy-labs/suasor/source-extract"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/source-extract.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 755 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00117 $0.00755
Opus 5 $0.00059 $0.00378
Sonnet 5 $0.00023 $0.00151
Haiku 4.5 $0.00012 $0.00076

Measured 5d ago against content hash 407d11f8d1a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

source-extract 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 5d 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.

Origin

This is a copy

86% identical to meeting-followup — 39 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

docs/skills/source-extract/SKILL.md · 45 lines

What it actually says

source-extract

特定 source の本文から task / decision / reply_draft 候補を抽出する HITL write skill(ADR-0004)。

いつ発火するか

  • 「この資料から task 抽出」「これに含まれる decisions 教えて」
  • <source_id> から候補を」「このドキュメントから ToDo 拾って」

何をするか(MCP tool flow)

read で本文を取り、write は HITL。auto-apply 経路は存在しないADR-0004)。

  1. 対象 source を特定する(externalId 不明なら search / find で確定)
  2. source.getexternalId)で対象 source の本文を読む
  3. propose.generate(mode=source_extract)で task / decision / reply_draft 候補を生成する(それぞれ TaskProposed / DecisionRecorded / ReplyDraftProposed 候補に対応、data-model.md
  4. propose.liststate=pending)で生成済み候補を一覧し、ユーザーに提示して確認を取る(native framing: ホスト側で人の承認を促す。Issue #89
  5. ユーザーが承認した候補のみ propose.apply で保存する(idempotent)。不要な候補は propose.reject(任意で理由)で却下する(却下は記録され、再 apply されない)

制約

  • HITL。人の承認なしに propose.apply を呼ばない。auto-apply しない。propose.list は read(候補確認)、propose.reject は却下の記録
  • 本 skill は手順書のみで実処理を持たない
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. 5d ago First seen · 45 lines · 117 tokens per session scan A 407d11f8d1a4

Subscribe to this mod's changes

source-extract is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 26d ago), licensed MIT. It adds 117 tokens to every session and 755 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to meeting-followup, differing in 39 lines, and is treated as a copy.