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 agentmods add commands/zenobia0000/cursor-agentic-coding-template/task-nextgit clone --depth 1 https://github.com/Zenobia0000/cursor-agentic-coding-templateWhat 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 | $0.00020 | $0.01216 |
| Opus 5 | $0.00010 | $0.00608 |
| Sonnet 5 | $0.00004 | $0.00243 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
task-next 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.
This is a copy
100% identical to task-next — 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
👨💼 TASK NEXT (PM Assistant v3)
您的專案經理小助手已上線。為您過濾上下文噪音，分析戰況，並從多個策略角度建議下一步的最佳行動。
1. PLAN 🎯 (規劃)
Objective
在您需要重新聚焦時，為您提供一份關於當前
memory-bank/current/tasks.md的摘要簡報，並從多個策略角度建議接下來應該執行的任務。此指令是一個只讀分析器，旨在幫助決策，不會修改tasks.md。
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 - 規劃與追蹤:
.cursor/rules/process/planning-process.md和.cursor/rules/process/task-tracking.md - 核心隔離:
.cursor/rules/isolation_rules/main.mdc
Prerequisites Check
在獲取簡報之前，請確保：
- ✅
tasks.md存在:memory-bank/current/tasks.md是您專案的「唯一真相來源」。 - ❌ Failure Action: 如果
tasks.md不存在，AI 必須建議用戶先運行/van來初始化專案。
2. DO 実行 (執行)
Core Process
PM 小助手將為您執行以下分析流程：
Step 0: 健康檢查 (Health Check)
- 檢查
tasks.md狀態: 驗證memory-bank/current/tasks.md是否存在、有效，且包含待辦任務。 - 批判性思考: 如果所有任務都已完成，AI 應報告：「恭喜！所有任務都已完成。建議執行
/reflect進行復盤。」 如果沒有可執行的任務（所有pending任務都被阻塞），AI 應報告：「目前沒有可立即開始的新任務，我們需要先完成正在進行中的『XXX』任務。」
Step 1: 記憶體互動 - 讀取 (Memory Interaction - Read)
- 讀取任務列表: 完整讀取並解析
memory-bank/current/tasks.md的內容。
Step 2: 多維度評估 (Multi-dimensional Evaluation)
- 識別候選者: 找出所有狀態為
pending且其依賴項均已completed的可執行任務。 - 評估視角: 從以下 PM 視角對每個候選任務進行評估：
- 👑 關鍵路徑 (Critical Path): 哪個任務是後續最多待辦任務的阻塞點？
- 💎 最高價值 (Highest Value): 哪個任務最貼近
projectbrief.md中定義的核心目標？ - ⚡️ 快速取勝 (Quick Win): 哪個任務預估工作量最小，可以快速完成以建立動能？
- 🛡️ 風險緩解 (Risk Mitigation): 哪個任務能解決最大的技術或業務不確定性？
Step 3: 記憶體互動 - 寫入 (Memory Interaction - Write)
- 輸出 PM 簡報: 將分析結果彙總成一份清晰、結構化的「PM 簡報」，作為輸出直接呈現給用戶。此指令不修改
tasks.md。 - (可選) 更新上下文: 可以在
memory-bank/current/activeContext.md中輕量地記錄一次「PM 簡報已提供」。
3. CHECK ✓ (檢查)
Verification Checklist
- 簡報是否清晰: 輸出的 PM 簡報是否易於理解，並清楚解釋了每個建議背後的原因？
- 只讀原則: AI 是否確保了沒有修改
tasks.md？
4. ACT 改善 (行動)
Finalization
- 等待用戶決策: AI 的任務在提供簡報後即完成，等待用戶做出最終決策。
Next Steps
AI 將根據用戶的決策，進入相應的模式。
- 👉 Primary Next Step: 用戶選擇一個建議後，AI 應準備執行
/creative或/implement指令，來處理被選中的任務。 - 💡 Alternative: 如果用戶認為所有建議都不合適，AI 應建議：「看起來我們的計畫可能需要調整。建議執行
/plan來重新審視和分解任務。」
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.
- 2d ago First seen · 66 lines · 20 tokens per session scan A cc0178a40903
task-next is a command published in the GitHub repository Zenobia0000/cursor-agentic-coding-template (5 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 1,216 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to task-next, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.