Caliber is a tool that generates and continuously updates AI context and configuration files for software repositories, including CLAUDE.md, AGENTS.md, and platform-specific rules. Development teams use it to keep coding agents aligned with the current codebase across tools such as Claude Code, Cursor, Codex, OpenCode, and GitHub Copilot. Its catalogue entries include skills, hooks, rules, instructions, and settings for configuring that workflow.
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.
git clone --depth 1 https://github.com/caliber-ai-org/ai-setupWrote 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/rules/caliber-ai-org/ai-setup/caliber-conventions)<a href="https://agentmods.dev/rules/caliber-ai-org/ai-setup/caliber-conventions"><img src="https://agentmods.dev/badge/rules/caliber-ai-org/ai-setup/caliber-conventions/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/rules/caliber-ai-org/ai-setup/caliber-conventions"><img src="https://agentmods.dev/badge/rules/caliber-ai-org/ai-setup/caliber-conventions.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 | $0.00196 | $0.00196 |
| Opus 5.5 | $0.00078 | $0.00078 |
| Sonnet 5.5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
caliber-conventions 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 1mo 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.
What it actually says
- ESM imports with
.jsextensions (even for.tssources) unknownoverany— ESLint warns on explicit any- Tests in
__tests__/dirs next to source, global setup insrc/test/setup.ts - Conventional commits:
feat:,fix:,refactor:,chore: - No hardcoded file→language mappings — detection is LLM-driven via
src/ai/detect.ts collectFingerprint()insrc/fingerprint/index.tsis async with internal LLM enrichment- Constants in
src/constants.tsandsrc/scoring/constants.ts resolveCaliber()fromsrc/lib/resolve-caliber.tsfor CLI binary path resolution- Dev branch:
next· Stable:master· Node >= 20
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.
- 1mo ago First seen · 14 lines · 196 tokens per session scan A def87f81dc58
caliber-conventions is a cursor rule published in the GitHub repository caliber-ai-org/ai-setup (1,309 stars, last pushed 26d ago), licensed MIT. It adds 196 tokens to every session, about $0.0008 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 2026-08-30.
Other cursor rules, from other repositories
coding-style
Coding style conventions for C#, TypeScript, Angular, and Python projects.
typescript
Rules for when building Javascript and/or Typescript projects.
commander
When using the commander.js NPM library.
typescript-strict-typing
Enforce strict TypeScript typing without any types.
hatch3r-typescript-patterns
TypeScript and JavaScript typing mechanics — satisfies over as, discriminated unions, branded types, strict utility types, barrel exports, and import ordering.
typescript
TypeScript style rules, scoped to .ts files.