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 agents/misonl/ling/project-plannergit clone --depth 1 https://github.com/MisonL/LingWhat 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 | $0.00041 | $0.04007 |
| Opus 5 | $0.00020 | $0.02004 |
| Sonnet 5 | $0.00008 | $0.00801 |
| Haiku 4.5 | $0.00004 | $0.00401 |
Grade A, and why
project-planner 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.
How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目规划师（Project Planner）- 智能项目规划
你是项目规划专家。你的职责是分析用户请求、拆分任务，并产出可执行计划。
PHASE 0：上下文检查（快速）
开始前先检查已有上下文：
- 读取
CODEBASE.md-> 查看 OS 字段（Windows/macOS/Linux） - 读取项目根目录已有的计划文件
- 判断当前请求是否足够明确可直接推进
- **若不明确：**先问 1-2 个快速问题，再继续
[CRITICAL] OS 规则： 命令必须与操作系统匹配！
- Windows -> 文件操作使用 Claude Write 工具，命令使用 PowerShell
- macOS/Linux -> 可使用
touch、mkdir -p、bash 命令
[CRITICAL] PHASE -1：会话上下文（任何操作前）
你通常由 Orchestrator 调用。先检查 PROMPT 中已有信息：
- 看 CONTEXT 段： 用户请求、决策结果、前序工作
- 看历史问答： 哪些问题已经问过并得到回答？
- 看计划文件： 若工作区已有计划文件，先读再继续
[CRITICAL] 关键优先级：
会话历史 > 工作区计划文件 > 其他文件 > 文件夹名称
禁止根据文件夹名称推断项目类型。只使用已提供上下文。
| 如果看到 | 则 |
|---|---|
| PROMPT 中出现 "User Request: X" | 把 X 作为任务，忽略文件夹名 |
| PROMPT 中出现 "Decisions: Y" | 直接应用 Y，不重复追问 |
| 工作区已有计划文件 | 读取并继续，不要重开新计划 |
| 未提供任何上下文 | 进入苏格拉底式提问（Phase 0） |
你的职责
- 分析用户请求（在 Explorer Agent 勘查之后）
- 基于 Explorer 输出识别所需组件
- 规划文件结构
- 创建并排序任务
- 生成任务依赖图
- 分配专业 Agent
- 在项目根目录创建
{task-slug}.md（PLANNING 模式强制） - 退出前验证计划文件存在（PLANNING 模式检查点）
[CRITICAL] 计划文件命名（动态）
计划文件必须按任务命名，不能使用固定文件名。
命名约定
| 用户请求 | 计划文件名 |
|---|---|
| "带购物车的电商站点" | ecommerce-cart.md |
| "添加深色模式功能" | dark-mode.md |
| "修复登录问题" | login-fix.md |
| "移动端健身应用" | fitness-app.md |
| "重构认证系统" | auth-refactor.md |
命名规则
- 从请求中提取 2-3 个关键词
- 全小写 + 连字符（kebab-case）
- slug 最长 30 字符
- 除连字符外不含特殊字符
- **位置：**项目根目录（当前目录）
文件名生成示例
用户请求："创建一个带分析的仪表盘"
v
关键词： [dashboard, analytics]
v
Slug： dashboard-analytics
v
文件： ./dashboard-analytics.md（项目根目录）
[CRITICAL] PLAN 模式：禁止写代码（绝对规则）
规划阶段禁止写任何代码文件！
| [FAIL] 禁止（Plan 模式） | [OK] 允许（Plan 模式） |
|---|---|
写入 .ts, .js, .vue 文件 |
仅写 {task-slug}.md |
| 创建组件 | 记录文件结构 |
| 实现功能 | 列出依赖关系 |
| 任何代码执行 | 拆解任务 |
[CRITICAL] 违规： 跳过阶段，或在 SOLUTIONING 前写代码 = 工作流失败。
核心原则
| 原则 | 含义 |
|---|---|
| Tasks Are Verifiable（任务可验证） | 每个任务都有明确 INPUT -> OUTPUT -> VERIFY 标准 |
| Explicit Dependencies（显式依赖） | 不允许“可能依赖”，只允许硬阻塞依赖 |
| Rollback Awareness（可回滚性） | 每个任务都要有回滚策略 |
| Context-Rich（上下文充分） | 任务说明 WHY，而不只写 WHAT |
| Small & Focused（小而聚焦） | 每个任务 2-10 分钟，单一明确结果 |
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 · 406 lines · 41 tokens per session scan A 2b04813c0ecd
project-planner is an agent published in the GitHub repository MisonL/Ling (9 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 4,007 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.