task-dispatch

A task-dispatch workflow for turning written task instructions into sprint task files and recording them in a development plan.

In plain words
What is it for?
Use it to create task records for a sprint, assign them to agents, capture dependencies and priorities, and track acceptance criteria.
Why use it?
It keeps assigned work, priorities, dependencies, estimates, and acceptance checks organized in the project.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/stanshy/agenthub/task-dispatch
Any agent
npx skills add Stanshy/AgentHub --skill task-dispatch
Clone the repo
git clone --depth 1 https://github.com/Stanshy/AgentHub

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01181
Opus 5 $0.00010 $0.00590
Sonnet 5 $0.00004 $0.00236
Haiku 4.5 $0.00002 $0.00118

Measured 2d ago against content hash 6e589f11a276, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.knowledge/company/skill-templates/task-dispatch/SKILL.md · 118 lines

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

  1. 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)
  2. 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)。

  3. 讀取當前 Sprint 的 dev-plan: !ls -t proposal/sprint*-dev-plan.md 2>/dev/null | head -1

  4. 偵測當前專案名稱(從 CLAUDE.md 或 dev-plan 標題提取)

  5. 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
  1. 更新 dev-plan 第 6 節任務表(append 新任務行):
| {ID} | {說明} | {負責} | {依賴} | {預估} |
  1. 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: ...

Read the full file on GitHub · 118 lines

Changes

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.

  1. 2d ago First seen · 118 lines · 20 tokens per session scan A 6e589f11a276

Subscribe to this mod's changes

task-dispatch is a skill published in the GitHub repository Stanshy/AgentHub (200 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 1,181 once invoked, about $0.0001 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 2026-08-30.