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 cafe3310/public-agent-skills --skill doc-todo-log-loopgit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote 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/cafe3310/public-agent-skills/doc-todo-log-loop)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/doc-todo-log-loop"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/doc-todo-log-loop/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/cafe3310/public-agent-skills/doc-todo-log-loop"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/doc-todo-log-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.01665 |
| Opus 5 | $0.00015 | $0.00833 |
| Sonnet 5 | $0.00006 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
doc-todo-log-loop 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: doc-todo-log-loop
1. 概述
文档驱动、日志记录的人机协作开发工作流。用户控制开发节奏,Agent 负责文档撰写、任务拆分、开发执行和日志记录。
2. 概念定义
以下为默认路径和命名约定。项目章程有特别约定时,以项目章程为准。
文档目录: 默认为项目根目录下backlog/,存放需求、设计、日志等文档TODO 文件: 默认项目根目录下TODO.md测试目录: 默认项目根目录下tests/文档命名:YYYY-MM-DD-HH-mm-{类别}-{标题}.md测试用例集命名:tests/{YYYY-MM-DD-HH-mm}-testsuite/测试用例命名:part{序号}-{模块}/case{序号}-{简述}.md,在测试用例集内部
3. 文档类别和编写风格
除了后面的工作流之外,若用户要求,Agent 可以随时写文档。
文档命名中的 {类别} 按以下分类取值:
开发日志: 开发过程、决策、问题及解决方式的记录。需求: 用户想要实现的功能或目标。仅含需求本身,不含实现细节。设计: 对即将实施任务的提前分析。子类别:系统设计、架构设计、交互设计、需求设计。规范: 定义广泛适用的规则、流程或标准。子类别:架构规范、代码规范、流程规范。说明: 对已完成技术实体的使用说明。子类别:接口说明、模块说明。调研: 对外部技术或资料的研究与对比分析。广泛搜索,记录来源,写出细节而非过度摘要。参考: 从外部摘录的原始资料。与调研的区别在于侧重原样引用而非主动分析。
文档的主要读者是未来的 Agent 和开发者。所有文档、过程日志与说明均保持精简、克制、平和、去形容词、去比喻化。无需冗长描述。记录人类决策、问题和修正方案。提供检索和理解所需的最小说明即可。
当用户指示或流程需要进行互联网调研时:广泛搜索相关资料;每找到一份资料,即记录为一份独立的调研文档,按命名约定命名;文档要记录来源,写出方案、观点、方法的细节,不要过度摘要。
4. 主要工作循环
本 Skill 定义的主要工作流由用户和 Agent 交替执行,遵循以下步骤:
步骤 1: 背景描述 → 文档撰写
- 触发: 用户提出功能目标或问题背景。
- Agent 行动:
- 与用户沟通,理解背景、目标、约束。
- 撰写需求描述文档(命名:
YYYY-MM-DD-HH-mm-需求-{简述}.md)。 - 如有 Plan Mode 中已接受的 Plan 文件,移动到文档目录并合理命名。
- 如项目含测试,在
tests/下准备对应的测试用例集(结构见「测试用例管理」一节)。
步骤 2: 需求描述 → TODO 拆分
- 触发: 用户基于文档或直接提出具体需求。
- Agent 行动:
- 将需求拆解为具体、原子化的待办事项,更新到
TODO.md。 - 每个事项关联
tests/中对应的测试用例。
- 将需求拆解为具体、原子化的待办事项,更新到
步骤 3: 任务指派
- 触发: 用户从
TODO.md中选择事项并明确指示执行。 - Agent 行动: 确认指令,了解必要文档,了解测试诉求,然后进入开发和验证。
步骤 4: 开发与验证
- 触发: 用户下达开发指令。
- Agent 行动:
- 执行开发任务。
- 每完成一个功能点,按关联的测试用例逐项验证(测试用例为人工检查清单,Agent 按步骤操作并记录结果)。
- 向用户报告时必须包含验证结果(通过/失败/待观察)。
- 用户进行最终确认。
- 约束: 验证未通过时,禁止声称任务完成。
步骤 5: 开发日志记录
- 触发: TODO 事项经用户确认完成后。
- Agent 行动:
- 撰写开发日志(命名:
YYYY-MM-DD-HH-mm-开发日志-{标题}.md),内容包括:- 实现了哪些功能点
- 对代码或项目结构的主要修改
- 遇到的问题及修正方式(包括用户和 Agent)
- 后续步骤建议
- 如经过测试,日志中包含验证结果:执行了哪些用例、对应的用例集版本、验证结论。
- 日志完成后,可查阅
TODO.md并向用户建议下一步任务,但不主动开始。
- 撰写开发日志(命名:
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.
- 10d ago First seen · 127 lines · 29 tokens per session scan A 0ded5427bee6
doc-todo-log-loop is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,665 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
firstsun-project-init
Bootstraps a firstsun-dev project end-to-end: selects relevant skills, scaffolds the agent harness, creates or reconciles the GitHub repository, applies repository metadata and README standards, and classifies the project under Firstsun Dev governance. New projects default to Workshop and are not automatically…
firstsun-pm
Expert project management for the Firstsun-Dev organization. This skill standardizes issue creation across multiple repositories, ensures all tasks are correctly linked to the central Project Board (#6), and enforces naming conventions. Trigger this whenever the user says "add a task", "create a ticket", "new job"…
monorepo-management
Master monorepo management. Use this to set up or optimize multi-package repositories using Turborepo, pnpm workspaces, or Nx.
gh-cli
GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
spec-kitty-mission-system
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 6-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…