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 skills/peltmonger/stardrive/stardrive-projectnpx skills add peltmonger/stardrive --skill stardrive-projectgit clone --depth 1 https://github.com/peltmonger/stardriveWrote 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/peltmonger/stardrive/stardrive-project)<a href="https://agentmods.dev/skills/peltmonger/stardrive/stardrive-project"><img src="https://agentmods.dev/badge/skills/peltmonger/stardrive/stardrive-project.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 | $0.00051 | $0.00572 |
| Opus 5 | $0.00026 | $0.00286 |
| Sonnet 5 | $0.00010 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
stardrive-project 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stardrive Project
Use Stardrive's repository guidance as the source of truth. Keep changes simple, accessible, and close to Astro defaults.
Start the right workflow
- For a new website, create a project with
npm create stardrive@latestunless the user already has a clone. - In an existing repository, read
AGENTS.mdbefore analyzing or editing anything. - Follow its bootstrap directive and the mode selected by
STARDRIVE_AGENT_MODE.md:project: build the user's website and follow.ai/PLAN.md; if the plan is absent, follow.ai/SETUP.md.boilerplate: maintain Stardrive itself and follow.ai/BOILERPLATE_MODE.md.
- Follow linked
.aiguides in their stated order. Do not activate unrelated setup guides merely by reading them.
If the repository lacks Stardrive's guidance files, confirm that it is actually a Stardrive project before applying these conventions. Consult the official repository and documentation when current boilerplate behavior is needed.
Implement changes
- Inspect
package.json,theme.config.ts, and nearby files before choosing an approach. - Prefer Astro and existing HTML. Use small vanilla JavaScript only when necessary; ask before adding a UI framework for complex interactivity.
- Keep one-off markup inline. Extract a component only for reuse, substantial self-contained complexity, or a clear reusable design primitive.
- Preserve the repository's existing i18n structure and styling conventions.
- Use SVG files as components or ordinary
imgelements, never through Astro'sImagecomponent. - Keep secrets and sensitive backend logic out of frontend code. Use a real backend service when private processing is required.
- Preserve semantic HTML, keyboard and touch operation, labels, focus behavior, and sufficient contrast.
- Avoid speculative abstractions and unrelated cleanup.
When functionality appears to have been removed from the boilerplate, check theme.config.ts and the official repository before rebuilding it. Ask whether restoring Stardrive's original implementation is preferable.
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 · 40 lines · 51 tokens per session scan A 1e66cbebf166
stardrive-project is a skill published in the GitHub repository peltmonger/stardrive (183 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 572 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
astro
Astro 7 conventions for ONE sites — plugin wiring via one.config.ts, OneChat/OneTrack placement, Cloudflare SSR. Invoke when editing .astro files or astro.config.mjs.
react19
React 19 conventions in ONE sites — client islands, @oneie/react hooks, no useEffect for ONE data. Invoke when editing .tsx components.
sdk
Use the ONE backend (@oneie/sdk) from this frontend via the plugin-backend wrapper. Invoke when reading/writing ONE data in API routes or SSR.
shadcn
The 33 primitives in src/components/ui/ are vendored shadcn. They are styled by the 6-token system — they reference CSS vars, never literal colors.
summarise
Summarises any document to the requested length.
astro-strapi-loader
Use @sensinum/astro-strapi-loader with Astro Content Layer: build Strapi REST query objects (object and object-array populate per REST parameters), let qs.stringify serialize—never inline query strings. Composable query fragments, dynamic zone "on", locale strategies, generateCollections, getCollection / getEntry.…