Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add RockyHong/super-bootstrap/plugin install 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/skills/rockyhong/super-bootstrap/todo)<a href="https://agentmods.dev/skills/rockyhong/super-bootstrap/todo"><img src="https://agentmods.dev/badge/skills/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 5.1 | $0.00184 | $0.02643 |
| Opus 5 | $0.00092 | $0.01321 |
| Sonnet 5 | $0.00037 | $0.00529 |
| Haiku 4.5 | $0.00018 | $0.00264 |
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 6d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Todo — Intent-Filtered Pipeline Scanner
Default render is the need-me board — momentum-driven, not a kanban: autonomously-drainable work collapses to one count line, and work that needs the human groups by venue category (decide / outward — your move / outward — waiting on others / device-bound / harness / probe) with a unblocks N fan-out signal. Bare invoke renders it immediately — no MCQ, no picker (a rendered surface the user navigates by typing a sub-verb, not a modal stop). Sub-verbs slice explicitly (deciding / drainable detail / on device Claude / touching the engine / flat everything). State reconstructed from open cards in docs/work/ (glob: {BUG|DEBT|GAP}-###.md), plus docs/test-queue.md and docs/outward/OUT-###.md when present (the scale module's test queue and outward folder). Pipeline state = card thread state (block presence drives stage classification).
Two render lanes, one classification SSOT (shared/classify-actionable.md): the script lane (primary) runs the bundled assets/render-board.py — a mechanical encoding of the spec, zero model tokens, sub-second — and the dispatch lane (fallback) runs the todo agent when the script fails.
Arguments
| Invocation | Behavior |
|---|---|
/super-bootstrap:todo |
Default. Render the need-me board (drainable→count, need-me grouped by venue category with fan-out). No mode-picker, no MCQ — dispatch immediately. |
/super-bootstrap:todo full |
Flat escape — every row (need-me + drainable), ungrouped, ranked. |
/super-bootstrap:todo discuss |
Decision shape — designs awaiting approval, surface verdicts pending the gateway's climb or the user's ruling, cards flagged for user decision, any row whose blocker is "user". Macro header on top. |
/super-bootstrap:todo cloud |
Cloud-safe filter — plan-writes for approved designs, executing plans on pure-logic surfaces, review-stage reads, doc cleanup, card triage. Macro header on top. |
/super-bootstrap:todo device |
Device-only filter — executing plans on UI / visual-e2e / manual surfaces, manual verification of review-stage plans. Macro header on top. |
/super-bootstrap:todo harness |
Harness filter — rows whose deliverable is the orchestration engine (CLAUDE.md, .claude/**, plugin-source harness files), grouped Deliberate (new doctrine) / Apply (existing doctrine, bounded site). Never mixed into the autonomous slices. Macro header on top. |
| any other value | Fallback. Dispatch mode: needme (the default board), and print this line above the relayed board: Unrecognized sub-verb '{value}' — rendering the default board. Modes: full · discuss · cloud · device · harness. Never map an unlisted value onto a listed mode by semantic proximity — this table is the whole set. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 131 lines · 184 tokens per session scan A f64a324c7656
todo is a skill published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 2,643 once invoked, about $0.0009 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 skills, from other repositories
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
phx-mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
manage-desktop-flows
Manage and run Power Automate Desktop (RPA) flows and machine groups. Use when the user asks about desktop flows, RPA, or machine groups.
quick
Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.
phx-freeze
Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.