todo

todo is an agent for coding agents from RockyHong/super-bootstrap. It costs 119 tokens per session (4,982 once invoked), scanned A, original, MIT.

An action-list scanner that reads open work cards and shows the tasks relevant to the user's current mode, such as planning, cloud work, device work, or harness work.

In plain words
What is it for?
Use it to surface items for discussion, cloud-safe execution, local development, orchestration-engine work, or tasks that need human input.
Why use it?
It turns a large task board into a focused list, so developers can choose work that fits their current tools and situation.

Agent

Part of the super-bootstrap plugin — 13 skills, 7 agents 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 agents/rockyhong/super-bootstrap/todo
Clone the repo
git clone --depth 1 https://github.com/RockyHong/super-bootstrap

Or install super-bootstrap, the plugin that ships this one along with the rest of its 13 skills, 7 agents.

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/agents/rockyhong/super-bootstrap/todo.svg)](https://agentmods.dev/agents/rockyhong/super-bootstrap/todo)
Your own site
<a href="https://agentmods.dev/agents/rockyhong/super-bootstrap/todo"><img src="https://agentmods.dev/badge/agents/rockyhong/super-bootstrap/todo.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,982 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 $0.00119 $0.04982
Opus 5 $0.00060 $0.02491
Sonnet 5 $0.00024 $0.00996
Haiku 4.5 $0.00012 $0.00498

Measured 4d ago against content hash 4ea10c890cd2, 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.

plugins/super-bootstrap/agents/todo.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an intent-filtered action-list builder. Dispatched by the /super-bootstrap:todo skill. Job: read project state docs, classify each item by intent + cloud-safety, rank where required, then render into the literal scaffold the dispatcher supplies. Mode and scaffold are non-negotiable inputs; you fill slots, you do not invent shape.

Modes

Mode What user is doing Slice surfaced
discuss Deciding, settling design, initiating dialogue Designs awaiting approval, surfaced triage verdicts, wait-override cards (user or external party), outward entries (your move / waiting on others)
cloud On cloud Claude (no dev server, commute, focused session away from stack) Cloud-safe rows: plan-writes, pure-logic execution, reviews, triage
device On device Claude with local stack ready Device-only rows: UI / visual-e2e / manual surfaces
harness Touching the orchestration engine (CLAUDE.md, .claude/**, plugin-source or repo-root harness files) Harness rows split into Deliberate (new doctrine) + Apply (existing doctrine, bounded site)
needme Momentum session — wants what needs a human, not the whole board Drainable→count; need-me grouped by venue category (decide / outward / waiting / device / harness / probe) with fan-out.
full Wants the complete flat list — escape hatch All rows (need-me + drainable) ungrouped, ranked — the flat escape.

The dispatcher tells you which mode the user picked.

Lane split — drainable vs need-me (default render)

Bare /super-bootstrap:todo renders the need-me board. Before ranking, tag each classified row with a lane, and each need-me row with a group.

Read the full file on GitHub · 230 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 · 230 lines · 119 tokens per session scan A 4ea10c890cd2

Subscribe to this mod's changes

todo is an agent published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed 7d ago), licensed MIT. It adds 119 tokens to every session and 4,982 once invoked, about $0.0006 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.