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 Stanshy/AgentHub --skill task-dispatchgit clone --depth 1 https://github.com/Stanshy/AgentHubWrote 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/stanshy/agenthub/task-dispatch)<a href="https://agentmods.dev/skills/stanshy/agenthub/task-dispatch"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/task-dispatch/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/stanshy/agenthub/task-dispatch"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/task-dispatch.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 | $0.00020 | $0.01181 |
| Opus 5.5 | $0.00008 | $0.00472 |
| Sonnet 5.5 | $0.00004 | $0.00236 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
task-dispatch 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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任務下達
老闆在 Session 中下達任務指令,自動建立 .tasks/sprint-{N}/ 並記錄到 dev-plan。
使用方式
/task-dispatch $ARGUMENTS
輸入格式
任務: T3 — 移除 19 個服務
指派: backend-architect
優先級: P0
依賴: T2
預估: 2h
驗收標準:
- 19 個服務檔案已刪除
- 保留 14 個核心服務
- typecheck 通過
支援批次(用 --- 分隔多個任務)。
執行步驟
-
解析
$ARGUMENTS,提取:- 任務 ID + 名稱(如
T3 — 移除 19 個服務) - 指派對象(agent-id)
- 優先級(P0/P1/P2,預設 P1)
- 依賴(可選,如
T2) - 預估工時(可選,如
2h) - 驗收標準(checkbox list)
- 任務 ID + 名稱(如
-
取得真實時間(必要,不可跳過): !
node -e "console.log(new Date().toISOString())"⚠️ 禁止自行編造時間。Agent 不知道真實時間,必須透過上述指令取得。將輸出存為變數
$NOW供後續步驟使用(用於建立時間和事件紀錄的 timestamp)。 -
讀取當前 Sprint 的 dev-plan: !
ls -t proposal/sprint*-dev-plan.md 2>/dev/null | head -1 -
偵測當前專案名稱(從 CLAUDE.md 或 dev-plan 標題提取)
-
為每個任務建立
.tasks/sprint-{N}/{ID}-{kebab-case}.md,使用以下格式:
⚠️ Sprint 子目錄規則:
- 從 dev-plan 標題或 Sprint 資訊判斷當前 Sprint 編號
- 建立目錄:
mkdir -p .tasks/sprint-{N}- 任務檔案路徑範例:
.tasks/sprint-1/T3-remove-services.md- 禁止 直接放在
.tasks/根目錄(會導致跨 Sprint ID 衝突)
欄位格式規範(系統解析依賴)
| 欄位 | 格式 | 範例 | 說明 |
|---|---|---|---|
| ID | TN |
T1, T3 |
T + 數字 |
| Sprint | Sprint N |
Sprint 1 |
必須此格式,系統靠名稱比對 DB 中的 Sprint UUID |
| 狀態 | 英文小寫 | created |
合法值:created/assigned/in_progress/in_review/blocked/done |
| 優先級 | P0/P1/P2 |
P0 |
— |
| 建立時間 | ISO 8601 | 2026-03-26T12:00:00.000Z |
— |
| 依賴 | 逗號分隔 ID | T1,T3 |
無依賴填 — |
| 並行組 | 字母或 — |
A |
同組任務可並行;循序任務填 — |
# {任務名稱}
| 欄位 | 值 |
|------|-----|
| ID | {ID} |
| 專案 | {專案名} |
| Sprint | Sprint {N} |
| 指派給 | {agent-id} |
| 優先級 | {P0/P1/P2} |
| 狀態 | assigned |
| 依賴 | {依賴任務 ID,無則填 —} |
| 並行組 | {A/B/C... 或 —} |
| 預估 | {預估工時,無則填 —} |
| 建立時間 | $NOW |
| 開始時間 | — |
| 完工時間 | — |
---
## 任務描述
{從指令中提取的任務說明}
## 驗收標準
- [ ] {逐項列出}
---
## 事件紀錄
### $NOW — 建立任務(assigned)
由老闆透過 /task-dispatch 派工
- 更新 dev-plan 第 6 節任務表(append 新任務行):
| {ID} | {說明} | {負責} | {依賴} | {預估} |
- 輸出摘要:
✅ 已建立 N 個任務:
- T3: 移除 19 個服務 → backend-architect (P0, 依賴 T2)
- T4: ...
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.
- 1mo ago First seen · 118 lines · 20 tokens per session scan A 6e589f11a276
task-dispatch is a skill published in the GitHub repository Stanshy/AgentHub (204 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 1,181 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
project-setup-info-local
Comprehensive setup steps to help the user create complete project structures in a VS Code workspace; this tool is designed for full project initialization and scaffolding, not for creating individual files. When to use this tool: user wants to create a new complete project from scratch; setting up entire project…
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
comet-native
A workflow for managing Native changes in Comet, where requirements, progress, and acceptance results are saved in project files. It uses the Comet command-line runtime to move through defined work stages.
comet-github-idea-to-issue
A workflow for turning a local idea, bug observation, or improvement proposal into a focused GitHub Issue draft. GitHub Issues are shared records for bugs, features, questions, and maintenance work.
generate-rfcs
Break the PRD into sequenced implementation RFCs under RFCs/ with an RFCS.md index, then cold-read each RFC for gaps.
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…