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/tdwhere123/do-it/do-it-handbookgit clone --depth 1 https://github.com/tdwhere123/do-itWrote 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/tdwhere123/do-it/do-it-handbook)<a href="https://agentmods.dev/commands/tdwhere123/do-it/do-it-handbook"><img src="https://agentmods.dev/badge/commands/tdwhere123/do-it/do-it-handbook.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.00750 |
| Opus 5 | $0.00023 | $0.00375 |
| Sonnet 5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
do-it-handbook 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 today.
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.
What it actually says
/do-it-handbook
为当前项目铺设长期有效的项目级文档骨架，让后续决策、编码与审查从同一份稳定事实出发。模板来源于 skills/do-it/do-it-handbook/templates/，全部是占位骨架，需要项目所有者填充实际内容。每天/每目标的过程记录写到 .do-it/worklog/，不要塞进 handbook。.do-it/plans/ 只放 durable execution contracts（Goal / Decisions / Boundary / Acceptance），不是进度日志。
调用方式
/do-it-handbook或/do-it-handbook init— 增量补齐缺失模板（推荐默认）/do-it-handbook list— 只列出当前项目缺失的模板，不写入/do-it-handbook check— 校验已有 handbook 文件名/位置是否对齐 do-it 模板列表
行为
- 加载
do-it-handbookskill。 - 检查
.do-it/handbook/是否存在；不存在则创建。 - 对比模板列表与项目现状，只写缺失的文件——已存在的不覆盖、不合并。
- 同时确保
.do-it/worklog/与.do-it/plans/有.gitkeep，且.do-it/CONTEXT.md存在——缺失时按do-it-context的三段骨架（Terms / Invariants / Relationships）写入，绝不覆盖 已有 CONTEXT / handbook / plan。缺失时写入.do-it/.gitignore（runtime / adaptive / events / sessions），不覆盖已有 ignore。不要创建.do-it/brainstorm/或.do-it/grill/；若用户目录已有内容，原样保留、不再推荐。 只有任务确实需要持久化时，才按do-it-decide写入 execution contract。 - 打印写入的文件清单 + "next steps" 提示，先填
invariants.md与glossary.md。
list / check 只对照 handbook 模板、CONTEXT、worklog、plans 与本地 ignore；缺失 brainstorm/grill 不算缺口。
不做什么
- 不自动
git add/git commit。 - 不覆盖任何已存在的 CONTEXT、handbook 文件或 plan。
- 不创建 brainstorm/grill，不删除用户已有 artifact。
- 不把 progress checkbox 写进 plan。
- 不基于代码自动生成项目特定内容——占位是有意的，等用户来填。
- 不改仓库根
.gitignore。
后续
填好 invariants 与 glossary 后，do-it-decide、do-it-code-quality 和 do-it-review 会在需要时读取它们。代码位置用 rg 或临时 code-mapper 重新发现；每日进展、证据和可复用经验写到 .do-it/worklog/YYYY-MM-DD.md 或 .do-it/worklog/<goal>.md。计划文件只在挣来时按 execution contract 持久化。
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.
- today Changed · +7 lines · +5 tokens per session ba721adafb32
- 4d ago First seen · 35 lines · 42 tokens per session scan A 004d4645d8a3
do-it-handbook is a command published in the GitHub repository tdwhere123/do-it (27 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 750 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 2026-08-30.
Other commands, from other repositories
forked
You are in a forked session - a conversation branched from a main working session to explore an issue, discuss options, or make decisions without polluting the main context window.
status
Check status of Kimi plugin jobs.
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.