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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/caliber-ai-org/ai-setupnpx agentmods add skills/caliber-ai-org/ai-setup/caliber-testingWrote 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/caliber-testing)<a href="https://agentmods.dev/skills/caliber-ai-org/ai-setup/caliber-testing"><img src="https://agentmods.dev/badge/skills/caliber-ai-org/ai-setup/caliber-testing/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/caliber-testing"><img src="https://agentmods.dev/badge/skills/caliber-ai-org/ai-setup/caliber-testing.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 | $0.00000 | $0.03248 |
| Opus 5.5 | $0.00000 | $0.01299 |
| Sonnet 5.5 | $0.00000 | $0.00650 |
| Haiku 4.5 | $0.00000 | $0.00325 |
Grade A, and why
caliber-testing scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Exec: `import { execSync } from 'child_process';` How it starts
The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caliber Testing
Critical
- All test files MUST be placed in
__tests__/directories parallel to source files:src/[module]/__tests__/[module].test.ts - Register any new
__tests__/directories invitest.config.ts'sincludeglob (already configured:src/**/*.test.ts) - NEVER mock
src/test/setup.ts— it is the global LLM provider mock already applied to all tests - Environment variable tests MUST save
process.envinbeforeEach, restore inafterEach, and explicitly delete env vars to test absence - Temporary file/directory cleanup MUST happen in
afterEach, not in individual test cleanup. Usefs.rmSync(dir, { recursive: true, force: true }) - When a test requires unmocking modules mocked in global setup, call
vi.unmock('../module.js')BEFORE the import statement - Run
pnpm testlocally andpnpm test:coveragebefore committing to verify coverage thresholds (lines: 50, functions: 50, branches: 50, statements: 50)
Instructions
Step 1: Create the test file in the correct directory
Create src/[module]/__tests__/[module].test.ts. The parent source file is src/[module]/[module].ts.
Verify: The __tests__ directory exists at the same level as the source file being tested.
Step 2: Import test framework
At the top of every test file, import from vitest:
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
Add additional imports based on what you're testing:
- File system:
import fs from 'fs'; import path from 'path'; import os from 'os'; - Temporary files: Use
fs.mkdtempSync(path.join(os.tmpdir(), 'caliber-prefix-')) - Exec:
import { execSync } from 'child_process';
Verify: All required test utilities are imported before test definitions.
Step 3: Set up module mocking (if needed)
If testing a module that imports other modules you want to mock:
vi.mock('../config.js', () => ({
loadConfig: vi.fn(),
writeConfigFile: vi.fn(),
}));
For complex mocks with test-time factory functions (hoisted):
const { mockLoadConfig } = vi.hoisted(() => ({
mockLoadConfig: vi.fn(),
}));
vi.mock('../config.js', () => ({
loadConfig: () => mockLoadConfig(),
}));
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 · 368 lines · 0 tokens per session scan A 8cdd36e800d8
caliber-testing is a skill published in the GitHub repository caliber-ai-org/ai-setup (1,309 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,248 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ralphctl-debugging-and-error-recovery
Systematic root-cause debugging. Use when tests fail, builds break, something that worked before broke, or behaviour does not match expectations — when you need to figure out what broke and why. Follow stop-the-line → reproduce → localize → reduce → root-cause → guard-with-regression-test → verify, not guessing; the…
test-writer
Write thorough, meaningful tests for any function, module, or API. Use when user asks to add tests, improve coverage, or ensure a piece of code is tested before shipping.
javascript-testing-patterns
Implement comprehensive testing strategies using Jest, Vitest, and Testing Library for unit tests, integration tests, and end-to-end testing with mocking, fixtures, and test-driven development. Use when writing JavaScript/TypeScript tests, setting up test infrastructure, or implementing TDD/BDD workflows.
generate-tests
Generate comprehensive tests for a file or function.
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.