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 skills add magnusrodseth/dotfiles --skill autoresearchgit clone --depth 1 https://github.com/magnusrodseth/dotfilesWrote 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/magnusrodseth/dotfiles/autoresearch)<a href="https://agentmods.dev/skills/magnusrodseth/dotfiles/autoresearch"><img src="https://agentmods.dev/badge/skills/magnusrodseth/dotfiles/autoresearch/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/magnusrodseth/dotfiles/autoresearch"><img src="https://agentmods.dev/badge/skills/magnusrodseth/dotfiles/autoresearch.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 | $0.00049 | $0.01263 |
| Opus 5 | $0.00024 | $0.00632 |
| Sonnet 5 | $0.00010 | $0.00253 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
autoresearch 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 9d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 9d ago First seen · 111 lines · 49 tokens per session scan A dbc5797a77d6
autoresearch is a skill published in the GitHub repository magnusrodseth/dotfiles (2 stars, last pushed today), with no licence file. It adds 49 tokens to every session and 1,263 once invoked, about $0.0002 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
batch-grill-me
A relentless interview that asks every frontier question at once, round by round.
modern-css
Specialized knowledge for writing modern high-quality CSS. Trigger this skill when starting a new CSS project/file, when the user asks about new CSS features (e.g. Masonry, View Transitions, Container Queries, Scroll-driven animations), or requests refactoring of legacy styles to modern standards.
npm-trusted-publishing
Set up or debug npm Trusted Publishing (OIDC) from GitHub Actions. Handles permissions, metadata validation, and provenance.
buildless-types
Use when the user asks to "set up types without a build step", "use vanilla JS with types", "configure erasable syntax", or mentions "JSDoc type checking". It provides instructions for modern type safety using JSDoc in browsers and native TypeScript execution in Node.js.
qmd-expert
How to effectively use QMD (Quick Markdown Search) to pull in extra relevant context, run multi-query searches, extract high-scoring chunk IDs, and fetch their contents. Use this skill when asked to search across a large markdown knowledge base, run QMD queries, or retrieve deep context using the qmd CLI.
pauls-project-setup
Paul's modern stack conventions for new projects (pnpm, native node test, esbuild, buildless-types). Consult when starting a new project or repository.