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-startgit 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-start)<a href="https://agentmods.dev/skills/stanshy/agenthub/task-start"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/task-start/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-start"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/task-start.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 | $0.00013 | $0.00896 |
| Opus 5.5 | $0.00005 | $0.00358 |
| Sonnet 5.5 | $0.00003 | $0.00179 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
task-start 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.
What it actually says
任務開始
Agent 開始執行任務時呼叫,將狀態從 assigned 改為 in_progress。
使用方式
/task-start <task-id>
參數
$0: 任務 ID(如T5)
執行步驟
- 找到對應的任務檔案(支援 Sprint 子目錄):
使用 Glob tool 搜尋
.tasks/**/$0-*.md,若無結果再搜尋.tasks/**/$0.md。 取得檔案路徑後用 Read tool 讀取內容。
任務檔案可能在
.tasks/sprint-{N}/T5-xxx.md,不再只在.tasks/根目錄。
-
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。 -
更新找到的任務檔案:
- 將
| 狀態 | ... |改為| 狀態 | in_progress | - 將
| 開始時間 | ... |改為| 開始時間 | $NOW | - 若
開始時間已有非—的值,不覆蓋(代表曾被 blocked 後恢復,保留首次開始時間) - 若找不到
| 開始時間 |欄位,在| 建立時間 |行之後插入| 開始時間 | $NOW |
- 將
-
依賴檢查(必要):
- 讀取任務檔的
| 依賴 |欄位 - 若不為
—,使用 Glob tool 逐一找到依賴任務檔,確認其| 狀態 |=done - 任一依賴狀態非
done→ 輸出 block 訊息並停止:⛔ $0 無法開始:依賴 {T?} 狀態為 {狀態},尚未完成 - 全部 done → 繼續
- 讀取任務檔的
-
事件紀錄(必要,不可跳過):在
## 事件紀錄區塊底部 append:### $NOW — 狀態變更 → in_progress 開始執行任務 -
Git Branch 處理: 讀取任務檔的
| 並行組 |欄位:若
並行組 = —(循序任務):- 確認當前 branch 為
sprint-{N}(從任務檔 Sprint 欄位取 N) - 若不在正確 branch,切換:
git checkout sprint-{N} - 輸出:
📌 循序任務,在 sprint-{N} 直接開發
若
並行組 = A/B/C...(並行任務):- 從任務標題產生 slug(小寫 kebab-case,最長 30 字元)
- 從 sprint-{N} 建立 task branch:
git checkout sprint-{N} git checkout -b task/s{N}-$0-{slug} - 輸出:
🌿 並行任務,已建立 branch: task/s{N}-$0-{slug}
- 確認當前 branch 為
-
輸出確認:
▶️ $0 狀態已更新為 in_progress
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 · 73 lines · 13 tokens per session scan A 158e77672edb
task-start is a skill published in the GitHub repository Stanshy/AgentHub (204 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 896 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.…