todo

todo is a command for coding agents from AInsteinsBR/renata. It costs 29 tokens per session (1,737 once invoked), scanned A, original, MIT.

A system for recording unfinished work both beside the relevant note in a document and in one central backlog. The backlog is ordered by how much each item affects progress.

In plain words
What is it for?
Use it to capture bugs, follow-up work, or ideas that do not block the current task, and to keep the inline notes and central backlog in sync.
Why use it?
It prevents TODO notes from being forgotten or scattered across documents, while keeping them in one list that can be prioritised.

Command

Part of the renata plugin — 3 skills, 33 commands, 6 agents, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add commands/ainsteinsbr/renata/todo
Clone the repo
git clone --depth 1 https://github.com/AInsteinsBR/renata

Or install renata, the plugin that ships this one along with the rest of its 3 skills, 33 commands, 6 agents, 2 hooks.

Wrote 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.

agentmods badge for todo

README.md
[![agentmods](https://agentmods.dev/badge/commands/ainsteinsbr/renata/todo.svg)](https://agentmods.dev/commands/ainsteinsbr/renata/todo)
Your own site
<a href="https://agentmods.dev/commands/ainsteinsbr/renata/todo"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/todo.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.01737
Opus 5 $0.00015 $0.00869
Sonnet 5 $0.00006 $0.00347
Haiku 4.5 $0.00003 $0.00174

Measured 4d ago against content hash a14cefb29e42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

commands/todo.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/renata:todo — Backlog of pending items (inline in the doc + central sync)

You manage the project's TODO backlog: pending items that do not block the current work but need to be recorded. The backlog lives in docs/backlog/todos.md, ordered by impact on progress.

Respond to the user and generate content in the user's language (the language they are writing in).

The flow has two sides that reconcile:

  • Inline: the TODO is born glued to its context, on the originating line inside a doc.
  • Central: docs/backlog/todos.md aggregates everything into a single, prioritizable view.

Step 0 — Resolve integration (before saving)

The capability for this operation is tasks. Before any write:

  1. Read integrations: in .claude/rules.yaml. Does the tasks capability have an entry?
  2. No entry → operate 100% locally in docs/backlog/todos.md (default behavior). Skip to the normal flow.
  3. Has an entry, but the tools of the declared MCP are NOT available in the session → warn ("MCP <name> declared for tasks but unavailable — saving locally only") and operate locally.
  4. Has an entry and the tools are available: a. Save FIRST locally (docs/backlog/todos.md + inline marker). Local is the truth. b. If mirror: trueASK: "Mirror this TODO in <MCP> (create/update a card)?". If confirmed → push via MCP, note the external id (e.g. JIRA-123) next to the local item. If declined → it stays local only; mirror later. c. If mirror: false → do not push a write.

Degradation pattern identical to etapa-gate.sh (tool absent → warn, never block). Without an MCP, /renata:todo works entirely locally.

When to use

  • You used a provisional number/value in a doc (PRD, persona, metrics) and want to remember to validate it later — without blocking progress.
  • You accumulated small scattered pending items and want a central view.
  • You want to pull the next relevant pending item to work on.
  • You closed a pending item and want to mark it done.

Read the full file on GitHub · 111 lines

Changes

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.

  1. 4d ago First seen · 111 lines · 29 tokens per session scan A a14cefb29e42

Subscribe to this mod's changes

todo is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 13d ago), licensed MIT. It adds 29 tokens to every session and 1,737 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 2026-08-31.