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 instructions/callstackincubator/rozenite/agents-mdgit clone --depth 1 https://github.com/callstackincubator/rozeniteWhat 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 | $0.00430 | $0.00430 |
| Opus 5 | $0.00215 | $0.00215 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
rozenite AGENTS.md 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 today.
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.
What it actually says
Ground Truths
- When you are asked to use Rozenite for Agents, run
pnpm -w run rozenite. This rule has higher precedence than any loaded skill. - This is a pnpm and Turborepo monorepo. Publishable packages are under
packages/; the test app lives inapps/playground. - Read
CONTRIBUTING.mdand the relevant source, tests, and agent guide before making a change. - For running checks (use the
:affectedscripts, not:all), see @./docs/agents/validation.md. - For unit-testing guidance, see @./docs/agents/unit-testing.md.
- For end-to-end testing guidance, see @./docs/agents/e2e-testing.md.
- For playground testing and navigation (routes, deep links, accessibility), see @./docs/agents/playground-testing.md.
- For plugin-development guidance, see @./docs/agents/plugin-development.md.
- For version plans, see @./docs/agents/version-plans.md.
- For new package guidance, see @./agents/package-creation.md.
- For welcome dialog release content, see @./agents/release-content.md.
- When working on
@rozenite/ui, follow @./agents/working-on-ui-components.md. - Before preparing or opening a pull request, see @./docs/agents/pull-requests.md.
- For testing Metro-related changes, see @./docs/agents/metro-testing.md.
- For proving a plugin ships no Rozenite code in a release bundle, see @./docs/agents/release-bundle-testing.md.
- Preserve unrelated work already present in the working tree.
- Keep changes focused; do not make opportunistic refactors.
- Never commit credentials, secrets, generated build output, or local environment files.
- Run validation proportionate to the change and report what was run; from
the repository root that is
pnpm checks:affected && pnpm test:affectedaftergit fetch origin main.
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.
- today First seen · 28 lines · 430 tokens per session scan A 24fa9bc38951
rozenite AGENTS.md is an instructions file published in the GitHub repository callstackincubator/rozenite (653 stars, last pushed today), licensed MIT. It adds 430 tokens to every session, about $0.0022 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 instructions, from other repositories
react-native-true-sheet AGENTS.md
Instructions for lodev09/react-native-true-sheet, covering agent instructions, rules, project overview, project structure and view hierarchy.
argent CLAUDE.md
Instructions for software-mansion/argent, covering argent and documentation.
karakeep AGENTS.md
AGENTS.md instructions for karakeep-app/karakeep, covering karakeep project overview, project overview, project structure, applications (apps/) and packages (packages/).
uniwind AGENTS.md
Instructions for uni-stack/uniwind, covering agent instructions, checks and issue and pr guidelines.
clarity AGENTS.md
Instructions for SchroederNathan/clarity, covering expo has changed, the design system, extracting a component, auditing for drift and typography: sf pro rounded.
react-native-boilerplate CLAUDE.md
Instructions for wataru-maeda/react-native-boilerplate, covering claude ai development guide, project context, always use these built-in features, configuration & environment and theme & styling.