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/wenhaochai/claude-plugins/todogit clone --depth 1 https://github.com/wenhaochai/claude-pluginsWrote 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/wenhaochai/claude-plugins/todo)<a href="https://agentmods.dev/commands/wenhaochai/claude-plugins/todo"><img src="https://agentmods.dev/badge/commands/wenhaochai/claude-plugins/todo.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 | $0.00022 | $0.03188 |
| Opus 5 | $0.00011 | $0.01594 |
| Sonnet 5 | $0.00004 | $0.00638 |
| Haiku 4.5 | $0.00002 | $0.00319 |
Grade A, and why
todo 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 5d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage ./TODO.md (project root by default). Supports read and write via a single command — the caller passes a natural-language description as $ARGUMENTS; branch on intent.
- No arguments → read-only rendering (see "Read mode" below).
- With arguments → infer intent (add / complete / delete / update) from the natural-language description and edit
./TODO.mdaccordingly (see "Write mode" below).
TODO.md format (authoritative)
Every item has live metadata (always-fresh one-liner + at most one next reminder) plus an append-at-top history log of dated progress entries in reverse chronological order.
Active item:
- [ ] Item title
- 备注:one-line summary of current state + next action
- 提醒:MM/DD/YYYY or 每天
- MM/DD:latest update
- MM/DD:earlier update
Completed item:
- [x] Item title
- 备注:final-state one-liner
- 完成:MM/DD/YYYY
- MM/DD:history entry
Core rules:
- Dates use
MM/DD/YYYY. - Titles stay short; detail goes in
- 备注:(live one-liner) and history entries. - 备注:is live, not append-only. Rewrite it on every update so it reflects "current state + next action" in a single sentence. Old context is preserved by the history log below, not by stacking context inside 备注.- At most one
- 提醒:per item, pointing to the next actionable date. When a reminder becomes moot (passed, superseded by newer info, no longer relevant), replace it with the next one — or delete it if nothing's pending. Never accumulate multiple 提醒 lines. - History entries (
- MM/DD:...) go in reverse chronological order — newest directly under the metadata lines, older ones below, separated by blank lines. Never overwrite or reorder existing entries. - Preserve quoted content (emails, Slack messages, replies) with
>blockquotes inside the relevant history entry. - No emphasis noise: avoid
**bold**,~~strikethrough~~, italics. Plain prose only. - Do not use a separate
- 状态:...field — status folds into- 备注:. - Group items under
## <category>headers (e.g.财务/报销,工作/沟通,生活/杂务,每月固定,每年固定). Pick the best fit; if none obvious, create a new one or put under## 杂项. - If
TODO.mddoes not exist, create it with a minimal header and the relevant category.
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.
- 5d ago First seen · 229 lines · 22 tokens per session scan A 2a22594cd943
todo is a command published in the GitHub repository wenhaochai/claude-plugins (16 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 3,188 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 commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.