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 agents/rockyhong/super-bootstrap/todogit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/agents/rockyhong/super-bootstrap/todo)<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>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 | $0.00119 | $0.04982 |
| Opus 5 | $0.00060 | $0.02491 |
| Sonnet 5 | $0.00024 | $0.00996 |
| Haiku 4.5 | $0.00012 | $0.00498 |
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.
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.
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.
- 4d ago First seen · 230 lines · 119 tokens per session scan A 4ea10c890cd2
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.
Other agents, from other repositories
GATE-NAMING
Agent "GATE-NAMING" from avelikiy/great_cto, covering gate naming convention, canonical gate names, universal gates (every archetype), conditional gates and archetype-specific gates.
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
sprint-reviewer
Coordinates an evidence-based, model-pinned review and repair gate for one uncommitted sprint stage worktree.
sprint-stage-runner
Runs one sprint stage end to end in its manual git worktree and delegates execution and review with the selected models.
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
sprint-review
Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…