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 agentmods add skills/ozzy-labs/suasor/reply-draftnpx skills add ozzy-labs/suasor --skill reply-draftgit 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/reply-draft)<a href="https://agentmods.dev/skills/ozzy-labs/suasor/reply-draft"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/reply-draft.svg" alt="Measured on agentmods" 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 | $0.00164 | $0.00971 |
| Opus 5 | $0.00082 | $0.00485 |
| Sonnet 5 | $0.00033 | $0.00194 |
| Haiku 4.5 | $0.00016 | $0.00097 |
Grade A, and why
reply-draft 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 4d 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.
What it actually says
reply-draft
返信下書きを生成する HITL write skill。生成だけでは送信も保存もしない（ADR-0004）。
いつ発火するか
- 「返信案を考えて」「これに返信したい」「この返信の下書き作って」
- 返信文脈（返信すべき相手・元メッセージ）が明示されているときだけ発火する。対象のない「下書き作って」は本 skill ではなく、告知・引き継ぎなら draft、計画なら plan-draft が受ける（
reply_to_source_idを要求して脱線しない）
何をするか（MCP tool flow）
write tool は HITL。auto-apply 経路は存在しない（ADR-0004）。
- 返信元 source を特定する（必要なら
source.get/searchでexternalIdを確定） propose.generate（mode=reply_draft、reply_to_source_id=<externalId>）で返信下書き候補を生成する。これはReplyDraftProposedevent（HITL・未適用、data-model.md）に対応する候補で、まだ確定・送信されないpropose.list（state=pending）で生成済みの下書き候補を一覧し、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）。不要な下書きは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 - 外部 SaaS への送信は行わない。ユーザーが下書きを確認して手で送る
- 下書きをファイルで欲しい場合は
draft.export（HITL write）で.md/.txtにローカル書き出しできる（送信はしない・ADR-0025） - 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.
- 4d ago First seen · 47 lines · 164 tokens per session scan A e2a6bf8ebe5b
reply-draft is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 25d ago), licensed MIT. It adds 164 tokens to every session and 971 once invoked, about $0.0008 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
content-publish
End-to-end content creation and publishing. Takes a topic (or generates one), drafts in the user's voice, gets approval via Telegram, and publishes to Medium via browser automation. Invoke with "publish a post about X", "write and publish to Medium", "content-publish", or when an ego-dispatched session needs to create…
mrsf-review
Review Markdown documents using the MRSF (Sidemark) sidecar format. Use when asked to review, comment on, or provide feedback on Markdown files. Adds structured, anchored review comments via the MRSF MCP server.
smoke-test
Use when interactively verifying the MTG MCP server works end-to-end by calling its MCP tools against real APIs.
new-provider
Scaffold a new backend provider following project patterns (service + provider + tests).
capture-fixture
Capture a live API response as a JSON test fixture for a given service and endpoint.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.