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 rules/caliber-ai-org/ai-setup/caliber-pre-commitgit clone --depth 1 https://github.com/caliber-ai-org/ai-setupWhat 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 | $0.00208 | $0.00208 |
| Opus 5 | $0.00104 | $0.00104 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
caliber-pre-commit 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 yesterday.
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
Before every git commit, check if the Caliber pre-commit hook is installed:
Run: grep -q "caliber" .git/hooks/pre-commit 2>/dev/null && echo "hook-active" || echo "no-hook"
If hook-active: just commit normally — Caliber syncs automatically via the hook. Tell the user: "Caliber will sync your agent configs automatically."
If no-hook: run caliber refresh && git add CLAUDE.md .claude/ .cursor/ .cursorrules .github/copilot-instructions.md .github/instructions/ AGENTS.md CALIBER_LEARNINGS.md 2>/dev/null before committing, and tell the user what was updated.
If caliber is not found, read the setup-caliber skill from .cursor/skills/setup-caliber/SKILL.md and follow its instructions to install Caliber.
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.
- yesterday First seen · 12 lines · 208 tokens per session scan A 82ab81f69959
caliber-pre-commit is a cursor rule published in the GitHub repository caliber-ai-org/ai-setup (1,255 stars, last pushed 1mo ago), licensed MIT. It adds 208 tokens to every session, about $0.0010 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 cursor rules, from other repositories
ui
React components must be functional and prop-typed.
cursorrules
DeepInit projection provenance (R3) stage: EMIT → PROJECT (cursor) runid: run-2026-06-13-kemal-e2e source: AGENTS.md (lean tier) — deterministic projection, no new findings note: content inside the DEEPINIT markers is owned + regenerated; edit OUTSIDE them. -->.
cursorrules
Cursor rule "cursorrules" from syf2211/ruledoctor, covering 订单服务项目规则（demo） and 硬性规则.
cursorrules
All agent instructions live in AGENTS.md (single source of truth). Do not add rules here.
integrations
External integration rules — providers, idempotency, bulkhead, observability.
main
Core coding standards enforced on all source files.