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 ozzy-labs/suasor --skill commitment-reviewgit clone --depth 1 https://github.com/ozzy-labs/suasorWrote 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/ozzy-labs/suasor/commitment-review)<a href="https://agentmods.dev/skills/ozzy-labs/suasor/commitment-review"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/commitment-review/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/ozzy-labs/suasor/commitment-review"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/commitment-review.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 | $0.00140 | $0.01428 |
| Opus 5.5 | $0.00056 | $0.00571 |
| Sonnet 5.5 | $0.00028 | $0.00286 |
| Haiku 4.5 | $0.00014 | $0.00143 |
Grade A, and why
commitment-review 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 2mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commitment-review
取り込み済み source から抽出した「約束/コミットメント」（"X までに Y する" の類）を台帳で HITL 管理する write skill。抽出は propose パイプラインに寄せ（ADR-0006 の ML 委譲境界を 1 本に保つ）、台帳の状態遷移（open / resolved / dismissed）を専用 write tool で行う（ADR-0021 / ADR-0004）。pair: 相手が負う約束（owed_to_me）の期限超過を能動的に催促する commitment-chase（read-only）。
いつ発火するか
- 「約束をスキャンして」「最近の約束を拾って」（抽出）
- 「誰に何を約束したっけ」「貸し借り確認」「コミットメント台帳」（確認）
- 「期限が来てる commitment」「この約束は完了」「これは誤検出」（解決）
何をするか（MCP tool flow）
read で集めて、write は HITL。auto-apply 経路は存在しない（ADR-0004）。
A. 抽出（scan）
propose.generate（mode=commitment_scan）で source からcommitment候補を生成する。各候補はtitle/direction（owed_by_me/owed_to_me）/dueDate?/person?/sourceExternalIds[]。重い推論はホスト側で行う（ADR-0006）propose.list（state=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（commitment候補はpropose.listのkindフィルタ対象外なので、mode/summaryで見分ける）- ユーザーが承認した候補のみ
propose.applyで適用する（CommitmentOpenedを append → 台帳にopen登録、idempotent）。不要な候補はpropose.reject（任意で理由）で却下する
B. 確認（list）
commitment.listで台帳を引く。state（open/resolved/dismissed）とdirection（owed_by_me/owed_to_me）でフィルタ、updated_atの時間窓も可- open な約束を direction 別（自分が負う / 相手が負う）に整理して提示する。
brief/next-actionsskill が demand と並べる「やるべきこと」signal と同じ台帳
C. 解決（state 遷移）
ユーザーの指示に従い、対象 commitment の状態を遷移させる（いずれも HITL・idempotent）:
commitment.set（state="resolved"） —open→resolved（果たした）commitment.set（state="dismissed"） —open→dismissed（誤検出 / 不要）commitment.set（state="open"） —resolved/dismissed→open（やり直し）
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.
- 2mo ago First seen · 66 lines · 140 tokens per session scan A 7ca59d0e522a
commitment-review is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 1,428 once invoked, about $0.0006 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
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
Profile
View, edit, or clear the LifeOS User Model (PRINCIPALIDENTITY.md) — persistent identity context loaded at session startup. Three intents: View, Edit (identity, goals, constraints, preferences), Clear (reset). Read by Algorithm OBSERVE and skills for personalization. USE WHEN profile, show profile, view profile, who am…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.