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 XRenSiu/claude-code-forge --skill planning-with-filesgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/planning-with-files)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/planning-with-files"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/planning-with-files/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/xrensiu/claude-code-forge/planning-with-files"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/planning-with-files.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 | $0.00108 | $0.01455 |
| Opus 5.5 | $0.00043 | $0.00582 |
| Sonnet 5.5 | $0.00022 | $0.00291 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
planning-with-files 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning with Files
核心原则
Context Window = RAM（易失、有限、昂贵）
Filesystem = Disk（持久、无限、便宜）
→ 重要信息写入磁盘，频繁重读保持注意力
→ 错误保留让模型学习，不要隐藏失败
三文件系统
| 文件 | 用途 | 更新时机 |
|---|---|---|
task_plan.md |
目标、阶段、决策、错误 | 阶段完成时、做决策时、遇到错误时 |
findings.md |
研究发现、技术笔记 | 每 2 次 view/browser 后必须更新 |
progress.md |
会话日志、测试结果 | 开始/结束阶段时、运行测试后 |
流程
启动任务
-
判断任务类型，选择模板：
- 研究型 →
templates/task_plan_research.md - 编码型 →
templates/task_plan_coding.md - 调试型 →
templates/task_plan_debug.md - 通用型 →
templates/task_plan.md
- 研究型 →
-
在项目目录创建三个文件（不是 skill 目录）：
cp ~/.claude/skills/planning-with-files/templates/task_plan.md ./task_plan.md cp ~/.claude/skills/planning-with-files/templates/findings.md ./findings.md cp ~/.claude/skills/planning-with-files/templates/progress.md ./progress.md -
填写 task_plan.md 的 Goal 部分
执行中
5 次规则：每执行 5 次工具调用后，重读 task_plan.md
- 将目标推到 context 末端，获得更多注意力
- 防止「Lost in the Middle」效应
2-Action 规则：每 2 次 view/browser 操作后，保存到 findings.md
- 防止信息只存在于 context 中然后丢失
- 强制外部化发现
错误追踪：遇到错误立即记录到 task_plan.md 的 Errors 部分
- 保留失败让模型「看到」
- 避免重复同样错误
会话恢复（5 问检查）
当 context 被清空或新会话开始时，回答这 5 个问题：
- 我在做什么？ → 读 task_plan.md 的 Goal
- 我做到哪了？ → 读 task_plan.md 的 Phases（找 CURRENT 标记）
- 我学到了什么？ → 读 findings.md
- 什么失败过？ → 读 task_plan.md 的 Errors
- 下一步是什么？ → 读 task_plan.md 的当前阶段
上下文压缩（当接近限制时）
- 将详细工具结果替换为文件路径
- 已完成阶段压缩为单行摘要
- 只保留最近 3 次工具结果的完整内容
- 其他信息确保已保存到三个文件中
完成任务
- 确认所有阶段标记为
[x] - 确认 findings.md 包含所有重要发现
- 更新 progress.md 的最终状态
- Stop hook 会自动验证
反模式
| 坏行为 | 为什么失败 | 正确做法 |
|---|---|---|
| 不创建计划直接开始 | 50+ 调用后忘记目标 | 必须先创建 task_plan.md |
| 信息只放 context | context 清空后丢失 | 写入文件系统 |
| 删除/隐藏错误 | 模型会重复错误 | 保留错误记录 |
| 长时间不重读计划 | 目标漂移 | 每 5 次调用重读 |
| 研究后不保存发现 | 信息丢失 | 每 2 次操作保存 |
| 在 skill 目录创建文件 | 文件位置错误 | 在项目目录创建 |
你可能想跳过这个流程
| 借口 | 反驳 |
|---|---|
| 「任务很简单」 | 简单任务更容易忘记细节 |
| 「我记得目标」 | 50 次调用后你不会记得 |
| 「写文件太慢」 | 重做比多花 30 秒更慢 |
| 「这次是特例」 | 没有特例，规则就是规则 |
| 「用户很急」 | 目标漂移导致的返工更浪费时间 |
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 2.6 KB
- references/compression.md 3.5 KB
- references/manus-principles.md 3.9 KB
- references/recovery.md 2.7 KB
- scripts/check-complete.ps1 4.1 KB runs code
- scripts/check-complete.sh 3.4 KB runs code
- scripts/init-session.ps1 4.4 KB runs code
- scripts/init-session.sh 4.7 KB runs code
- templates/coding_plan.md 2.0 KB
- templates/findings.md 1.3 KB
- templates/generic_plan.md 1.3 KB
- templates/progress.md 2.0 KB
- templates/research_plan.md 2.1 KB
- templates/task_plan_coding.md 1.6 KB
- templates/task_plan_debug.md 2.2 KB
- templates/task_plan_research.md 2.0 KB
- templates/task_plan.md 1.3 KB
- tests/pressure-tests.md 4.3 KB
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 · 145 lines · 108 tokens per session scan A a22697eb2882
planning-with-files is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 108 tokens to every session and 1,455 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.