Borrowing it
Nothing to install: this file belongs to Zenobia0000/cursor-agentic-coding-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Zenobia0000/cursor-agentic-coding-template/main/.cursor/commands/task-init.mdgit clone --depth 1 https://github.com/Zenobia0000/cursor-agentic-coding-templateWrote 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/commands/zenobia0000/cursor-agentic-coding-template/task-init)<a href="https://agentmods.dev/commands/zenobia0000/cursor-agentic-coding-template/task-init"><img src="https://agentmods.dev/badge/commands/zenobia0000/cursor-agentic-coding-template/task-init/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/commands/zenobia0000/cursor-agentic-coding-template/task-init"><img src="https://agentmods.dev/badge/commands/zenobia0000/cursor-agentic-coding-template/task-init.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 | $0.00018 | $0.01131 |
| Opus 5.5 | $0.00007 | $0.00452 |
| Sonnet 5.5 | $0.00004 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
task-init 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 2mo 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.
This is a copy
100% identical to task-init — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚀 TASK INIT (v3)
為一次新的冒險啟航！將用戶的模糊想法，轉化為一個清晰、可追蹤的任務 Epic。
1. PLAN 🎯 (規劃)
Objective
將一個新的、高層次的用戶需求，轉化為一個結構化的 Epic 任務，並在用戶確認後，將其添加到
memory-bank/current/tasks.md的頂部，作為後續/plan指令的輸入。
Guiding Rules
在執行此指令時，AI Agent 必須遵循以下規則：
- 主要規則:
.cursor/rules/principles/global.mdc - 規劃流程:
.cursor/rules/process/planning-process.md - 核心隔離:
.cursor/rules/isolation_rules/main.mdc
Prerequisites Check
在初始化一個新任務之前，請確保：
- ✅
tasks.md存在: 核心任務文件memory-bank/current/tasks.md已由/van指令創建。 - ✅ 需求已提供: 用戶已提出一個新的目標或需求。
- ❌ Failure Action: 如果
tasks.md不存在，AI 應建議先運行/van。
2. DO 実行 (執行)
Core Process
遵循一個從需求到 Epic 的結構化轉化流程：
Step 0: 健康檢查 (Health Check)
- 檢查需求清晰度: 分析用戶的請求。
- 批判性思考: 如果用戶的需求極度模糊 (e.g., "給我做個 AI")，AI 必須通過提問來引導用戶聚焦。
Step 1: 記憶體互動 - 讀取 (Memory Interaction - Read)
- 讀取用戶需求: 這是本指令的主要輸入。
- (可選) 讀取專案簡報: 快速掃描
memory-bank/current/projectbrief.md，以確保新任務與專案大方向一致。
Step 2: 結構化分析 (Structured Analysis)
- 定義目標 (Goal): 用一句話總結任務的最終目標。
- 定義驗收條件 (DoD): 列出 3-5 個關鍵的、可衡量的「完成定義」。
- 初步分解 (WBS): 創建一個非常高層次的階段劃分。
- 風險評估 (Risks): 識別 1-3 個最顯而易見的風險。
Step 3: 記憶體互動 - 確認與寫入 (Memory Interaction - Confirm & Write)
- 向用戶確認 (Confirm): 將上述分析結果，以一個清晰的「任務提案」形式呈現給用戶，並請求批准。
- 追加寫入
tasks.md(Append): 在得到用戶肯定的答覆後，將這個結構化的 Epic 任務追加到memory-bank/current/tasks.md文件的頂部。注意：是追加 (append)，不是覆蓋 (overwrite)。
3. CHECK ✓ (檢查)
Verification Checklist
- 提案是否清晰: AI 生成的「任務提案」是否準確且簡潔地反映了用戶的需求？
- 用戶是否確認: AI 是否在寫入
tasks.md之前，獲得了用戶的明確批准？ -
tasks.md是否已更新: 檢查memory-bank/current/tasks.md文件，確認新的 Epic 任務是否已成功追加。
4. ACT 改善 (行動)
Finalization
- 報告完成: 在更新
tasks.md後，向用戶報告。例如：「好的，我已經將『XXX』任務作為一個新的 Epic 添加到我們的計畫中。」
Next Steps
Epic 的創建是詳細規劃的開始。
- 👉 Primary Next Step: 執行
/plan指令。/plan指令會讀取剛剛創建的 Epic，並將其進一步分解為詳細的、可執行的子任務。 - 💡 Alternative: 如果識別出的風險非常高，可以先執行一個研究性質的任務 (Spike)，對不確定的技術點進行預研。
TASK INIT (v3) 已啟動。正在聆聽您的新想法，並準備將其轉化為行動藍圖...
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.
- 2mo ago First seen · 68 lines · 18 tokens per session scan A 5cff098c61be
task-init is a command published in the GitHub repository Zenobia0000/cursor-agentic-coding-template (5 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 1,131 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to task-init, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.