Borrowing it
Nothing to install: this file belongs to haakonbull/autosprint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/haakonbull/autosprint/master/.claude/skills/todos/SKILL.mdgit clone --depth 1 https://github.com/haakonbull/autosprintWrote 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/haakonbull/autosprint/todos)<a href="https://agentmods.dev/skills/haakonbull/autosprint/todos"><img src="https://agentmods.dev/badge/skills/haakonbull/autosprint/todos/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/haakonbull/autosprint/todos"><img src="https://agentmods.dev/badge/skills/haakonbull/autosprint/todos.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00096 | $0.00646 |
| Opus 5.5 | $0.00038 | $0.00258 |
| Sonnet 5.5 | $0.00019 | $0.00129 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
todos 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 2mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read todos.md at the repo root and execute each unchecked task in it.
File format
todos.md is a plain list of tasks. Conventions:
- Each
[](or[ ]) on its own line marks the start of a task. The lines below it — up to the next[]line, or end of file — are the task description. - Leading content above the first
[](if any) is the first task, even if it has no explicit[]marker. [x]means completed — skip it.- Completely blank sections between tasks are decorative; ignore them.
What to do
- Read
todos.md. - Parse it into an ordered list of tasks. For each task, capture whether it's
[](pending) or[x](done). - For each pending task, in order:
- Re-read the task description carefully.
- Decide what the user is asking for. If unclear, ask one concise question before proceeding.
- Do the work — code changes, file edits, whatever the task requires.
- Run the project's tests or other obvious validation if applicable.
- Only when the task is genuinely complete, edit
todos.mdto change that task's[]to[x]. Leave the description intact. - If the task was the leading-content task with no explicit marker, add an
[x]marker line immediately above it so future runs skip it.
- Re-read
todos.mdone last time after the final pending task. The user often adds new[]items while tasks are running — any new pending items that appeared during the session must be picked up before ending. If new items exist, loop back to step 3. - After the last pending task is done (or if a task blocks on a question), summarise what was completed and what is still pending.
- End-of-run summary. Write a short summary in chat of what was completed and what is still pending.
What not to do
- Do not delete or reorder the task descriptions. Only change the checkbox.
- Do not batch the mark-as-done edits — mark each task done as soon as it is actually done, so a crash mid-run never loses track.
- Do not skip ahead. Tasks are listed in intended order.
- Do not invent new tasks. The file is authoritative.
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.
- 2mo ago First seen · 42 lines · 96 tokens per session scan A 256d1e61b17d
todos is a skill published in the GitHub repository haakonbull/autosprint (5 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 646 once invoked, about $0.0004 per session on Opus 5.5. 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.
todos compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| todoshaakonbull/autosprint | Skill | 5 | 4d ago | MIT | A | 96 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |