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 inbox-triagegit 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/inbox-triage)<a href="https://agentmods.dev/skills/ozzy-labs/suasor/inbox-triage"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/inbox-triage/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/inbox-triage"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/inbox-triage.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 | $0.00149 | $0.01319 |
| Opus 5 | $0.00075 | $0.00660 |
| Sonnet 5 | $0.00030 | $0.00264 |
| Haiku 4.5 | $0.00015 | $0.00132 |
Grade A, and why
inbox-triage 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 11d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
inbox-triage
未処理 inbox を仕分ける HITL write skill。各アイテムを task 化 / decision 記録 / dismiss する action 候補を提案し、承認分のみ適用する（ADR-0004）。
いつ発火するか
- 「受信箱整理して」「inbox 仕分けて」「未処理アイテム捌いて」「受信箱を空にして」
- 「pending」語彙（保留中の提案候補の確認・承認）は proposal-review が受ける。本 skill が捌くのは受信箱（
inbox.list）の未処理アイテム
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）。
inbox.list（state=open）で未処理アイテムを集める。各 item はsource_external_id/state/updated_atpropose.generate（mode=inbox_triage）で各アイテムへの action 候補を生成する。候補は次のいずれか:- task 化 —
task.create（write tool）に渡す task 候補。TaskProposedevent に対応 - decision 記録 —
DecisionRecordedに対応する候補 - 仕分け —
InboxItemTriaged（state: snoozed / done / dismissed）に対応する候補
- task 化 —
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（native framing: ホスト側で人の承認を促す。Issue #89）- ユーザーが承認した候補のみ
propose.applyで保存する（idempotent）。task 化を含む場合も承認後に適用する。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）
直接書込ループ（inbox.add / inbox.triage・Issue #88）
propose.* 経由のモデル提案に対し、人自身の捕捉・解決は直接 write tool でも行える（いずれも HITL）:
inbox.add（sourceExternalId）— source をopenで捕捉するinbox.triage（inboxId/action=task/decision/discard）—open項目を解決する。task/decisionは source 由来の task/decision を生成し項目をdoneに、discardはdismissedに遷移する。生成 entity はtask.create/decision.recordと同一の content 由来 identity に着地する（live な同一内容 task は再利用、completed/droppedの一致のみなら新規 task を採番。#435）。open以外の項目を triage しようとすると拒否される（state machine）
制約
- HITL。人の承認なしに
propose.apply/task.create/inbox.add/inbox.triage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 inbox.stateの語彙:open/snoozed/done/dismissed（data-model.md）。inbox.triageはopen→done（task/decision）/dismissed（discard）の遷移のみ- 本 skill は手順書のみで実処理を持たない
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.
- 11d ago First seen · 59 lines · 149 tokens per session scan A 120c9f948be6
inbox-triage is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 1,319 once invoked, about $0.0007 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
email-management
Inbox management workflow — triage, batching, folder strategy, and inbox zero maintenance.
mk:context-engineering
Runtime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when…
janitor-swipe
Tinder for your Claude Code skills. Reviews a sorted deck of every installed skill and lets you swipe keep / delete / skip on each one. Use when the user wants to bulk-clean their skill collection, triage unused skills, or do interactive skill cleanup. Trigger with '/janitor-swipe'.
email-triage
Triage Joel's email inboxes via the joelclaw email CLI. Scan, categorize, archive noise, surface actionable items, and draft replies. Use when: 'check my email', 'scan inbox', 'triage email', 'what needs a reply', 'clean up inbox', 'archive junk', 'email summary', 'anything important in email', or any request…
pilot-inbox
Unified inbox for all incoming items — messages, files, and trust requests in one view. Use this skill when: 1. You need to check all incoming items at once 2. You want to triage and prioritize incoming communications 3. You need a central location to review pending items Do NOT use this skill when: - You need to send…
inbox-triage
Email inbox triage for AI agents — scan, categorize, draft replies, surface urgent items, and archive noise. Supports Gmail and IMAP for inbox zero workflows.