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 task-publishgit 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/task-publish)<a href="https://agentmods.dev/skills/ozzy-labs/suasor/task-publish"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/task-publish/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/task-publish"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/task-publish.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 | $0.00128 | $0.01531 |
| Opus 5 | $0.00064 | $0.00766 |
| Sonnet 5 | $0.00026 | $0.00306 |
| Haiku 4.5 | $0.00013 | $0.00153 |
Grade A, and why
task-publish 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 8d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task-publish
確定タスクを外部ホーム（GitHub Issues / Jira / Slack List）へ起票し、状態を遠隔操作する HITL write skill（ADR-0036 / ADR-0004）。Suasor は「横断捕捉・AI 提案・優先付け・由来」に徹し、公開したタスクの住処は外部ツールに委ねる（single pane）。ホームは destination（github / jira / slack）ごとに独立設定でき、task.publish は任意の destination 引数（省略時 [tasks].default）で行き先を選ぶ（ADR-0036 改訂 R1-2）。tasks projection は published task については状態の正本ではなく、優先ビュー表示用の読み取りキャッシュ + provenance（状態の正本は外部ホーム＝D1）。未 publish タスクは private tier（ローカルが正本・R1-4）。task-update が Suasor 内 lifecycle を動かすのに対し、本 skill は外部への egress write / 遠隔操作を担う。
いつ発火するか
- 「このタスク GitHub に起票して」「タスクを外部に publish して」（→
task.publish） - 「Jira のチケット完了にして」「あの ticket を done に」（→
task.actcomplete） - 「再オープンして」「やっぱり open に戻して」（→
task.actreopen） - 「あの issue にコメント付けて」「進捗をコメントしといて」（→
task.actcomment）
何をするか（MCP tool flow）
read で対象を特定して、egress write は HITL。auto-apply 経路は存在しない（ADR-0004）。egress（外部送信）を伴うため、ローカル draft.export 以上に確認は厳格にする（ADR-0003 §egress 境界）。
task.list（stateで絞り可）で対象 task を特定する。各 task はid/title/state/ 既存の外部 id（publish 済みか）- どの task をどのホーム（GitHub / Jira / Slack List）にどう操作するかを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）。送信先・本文（コメント等）を明示する
- 承認後:
- 未起票の確定タスク →
task.publish（任意destinationor[tasks].defaultの[tasks.homes.<destination>]へ起票。TaskPublishedを append、外部 id を記録） - 起票済みタスク →
task.act（complete/reopen/comment。TaskActionIssuedを append）。actuator 設定はその task 自身のpublished_destinationで解決される（R1-3）ので、既定を乗り換えても既存 published task の操作は壊れない
- 未起票の確定タスク →
制約
- HITL。人の承認なしに
task.publish/task.actを呼ばない。auto-apply しない。task.listは read（特定） - 行き先は destination ごとの typed ホーム（ADR-0036 改訂 R1）。
task.publishの任意destination引数（省略時[tasks].default）で振り分ける（R1-2）。公開済み task の操作/読み戻しは task 自身のpublished_destinationで config 解決（R1-3） - 冪等・二重起票回避: actuator は冪等 label（例
suasor+suasor-task-<id>）で同一タスクの重複起票を防ぐ。「外部起票成功 → ローカル event append 失敗」の二重起票リスクに注意し、再実行時は既存外部 id を確認してから操作する - connector（read 専用・ADR-0007）と actuator（write）は型レベルで別 capability。actuator 未実装のソースへは publish できない（status で報告、throw しない）
- Slack List actuator は comment 非対応など、ホームごとに対応操作に差がある（ADR-0036）。非対応操作は
unsupportedとして報告する - 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.
- 8d ago First seen · 50 lines · 128 tokens per session scan A cab5731cd1ce
task-publish is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 29d ago), licensed MIT. It adds 128 tokens to every session and 1,531 once invoked, about $0.0006 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
agentrq
Lead multiple agents to accomplish big tasks with specialized workspaces/agents by assigning tasks to specialized agents.
agentrq
Execute tasks assigned by humans or supervisor agents within a specific AgentRQ workspace. Use when you receive channel messages or need to report progress on tasks.
run-task
Execute a single Todo task through In Progress to Review, meeting every acceptance criterion with tests and vibe-lint checks. Refuses Planning-status tasks. Invoked as /agiflow:run-task . Uses gettask, updatetask, createtaskcomment.
bbs-relay-pickup
A coordination procedure for agents that share work on tasks through a BBS task system, where BBS is the service used to claim, run, and report task steps.
acceptance-orchestrator-v2
Acceptance Orchestrator workflow skill. Use this skill when the user needs a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention and the operator should preserve the upstream workflow, copied support files…
feishu-pm
Project Management skill for Feishu Bitables. Add tasks, list records, and track progress directly from the agent.