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.
npx skills add caliber-ai-org/ai-setup --skill find-skillsgit 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/skills/caliber-ai-org/ai-setup/find-skills)<a href="https://agentmods.dev/skills/caliber-ai-org/ai-setup/find-skills"><img src="https://agentmods.dev/badge/skills/caliber-ai-org/ai-setup/find-skills/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/caliber-ai-org/ai-setup/find-skills"><img src="https://agentmods.dev/badge/skills/caliber-ai-org/ai-setup/find-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.00528 |
| Opus 5 | $0.00038 | $0.00264 |
| Sonnet 5 | $0.00015 | $0.00106 |
| Haiku 4.5 | $0.00008 | $0.00053 |
Grade A, and why
find-skills 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 11d 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
Find Skills
Search the public skill registry for community-contributed skills relevant to the user's current task and install them into this project.
Instructions
- Identify the key technologies, frameworks, or task types from the user's request that might have community skills available
- Ask the user: "Would you like me to search for community skills for [identified technologies]?"
- If the user agrees, run:
This outputs the top 5 matching skills with scores and descriptions.caliber skills --query "<relevant terms>" - Present the results to the user and ask which ones to install
- Install the selected skills:
caliber skills --install <slug1>,<slug2> - Read the installed SKILL.md files to load them into your current context so you can use them immediately in this session
- Summarize what was installed and continue with the user's task
Examples
User: "let's build a web app using React"
-> "I notice you want to work with React. Would you like me to search
for community skills that could help with React development?"
-> If yes: run caliber skills --query "react frontend"
-> Show the user the results, ask which to install
-> Run caliber skills --install <selected-slugs>
-> Read the installed files and continue
User: "help me set up Docker for this project"
-> "Would you like me to search for Docker-related skills?"
-> If yes: run caliber skills --query "docker deployment"
User: "I need to write tests for this Python ML pipeline"
-> "Would you like me to find skills for Python ML testing?"
-> If yes: run caliber skills --query "python machine-learning testing"
When NOT to trigger
- The user is working within an already well-configured area
- You already suggested skills for this technology in this session
- The user is in the middle of urgent debugging or time-sensitive work
- The technology is too generic (e.g. just "code" or "programming")
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.
- 11d ago First seen · 55 lines · 76 tokens per session scan A a987a8d9d19a
find-skills is a skill published in the GitHub repository caliber-ai-org/ai-setup (1,267 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 528 once invoked, about $0.0004 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
web-access
A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.
skill-creator
A skill for creating or improving reusable instructions for an agent. It covers capturing the intended workflow, writing a draft, testing it, and refining its trigger description.
packing-list
A travel-packing aid that builds a checklist from the destination's climate, trip type, length, transport, accommodation, and travelling group. It treats a city break, hike, business trip, and family holiday as different packing problems.
repo
Repository operating rules for verified Mythos edits.
implementing-jsc-classes-cpp
Implements JavaScript classes in C++ using JavaScriptCore. Use when creating new JS classes with C++ bindings, prototypes, or constructors.
duel-agents
Configure and use Duel Agents model routing in Claude Code. Requires a Duel API key from duelagents.com. Routes all LLM traffic through duelagents.com/v1.