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 agentmods add skills/caliber-ai-org/ai-setup/writers-patternnpx skills add caliber-ai-org/ai-setup --skill writers-patterngit 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/writers-pattern)<a href="https://agentmods.dev/skills/caliber-ai-org/ai-setup/writers-pattern"><img src="https://agentmods.dev/badge/skills/caliber-ai-org/ai-setup/writers-pattern.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.03775 |
| Opus 5 | $0.00056 | $0.01887 |
| Sonnet 5 | $0.00022 | $0.00755 |
| Haiku 4.5 | $0.00011 | $0.00378 |
Grade A, and why
writers-pattern 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform Writer Pattern
Critical
-
Every writer MUST:
- Export a single named function:
write<Platform>Config(config: <PlatformConfig>): string[] - Accept a platform-specific config interface defining what content to write
- Return
string[]of all written file paths (used by manifest and progress display) - Create parent directories with
fs.mkdirSync(dir, { recursive: true })before writing files - Wrap skill frontmatter exactly as shown in Step 4 (YAML between
---markers) - NOT modify files outside the intended platform directories (e.g., Claude writer only touches
.claude/,CLAUDE.md,.mcp.json)
- Export a single named function:
-
Integration point: Every writer MUST be imported and called in
src/writers/index.tswithin thewriteSetup()function. Missing this step means the writer will never execute. -
Validation before Step 1: Verify the platform name is unique (
ls src/writers/shows no<platform>/index.ts). If it exists, you are modifying, not adding.
Instructions
Step 1: Define the Platform Config Interface
Verify the platform name is unique (see Critical). Create src/writers/<platform>/index.ts.
At the top of the file, define a config interface that describes all content the writer accepts. The interface MUST include:
- A main markdown/text file (e.g.,
claudeMd,cursorrules,agentsMd,instructions) - Optional nested arrays:
rules,skills,mcpServers,instructionFiles, etc. - Each rule/skill/file has at minimum:
nameorfilename,content, and for skills,description
Example (matching GitHub Copilot pattern already in codebase):
interface CopilotConfig {
instructions: string; // Main content
instructionFiles?: Array<{ filename: string; content: string }>;
}
Validation: Confirm the interface property names match platform conventions (e.g., Claude uses claudeMd, Cursor uses cursorrules). Check existing writers: src/writers/claude/index.ts line 9, src/writers/cursor/index.ts line 9, src/writers/codex/index.ts line 5.
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.
- 5d ago First seen · 268 lines · 111 tokens per session scan A ea18f96e4f9e
writers-pattern is a skill published in the GitHub repository caliber-ai-org/ai-setup (1,259 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 3,775 once invoked, about $0.0006 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
bridge
Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules…
prompt-optimization
Use this skill when the user wants to optimize, modify, or improve the system prompt of an AI agent. This includes requests like 'optimize the prompt', 'make the AI more focused on X', 'change the system prompt', 'improve the agent behavior', or 'modify how the AI responds'.
fable-method
A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no…
fable-domain
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain ", "make a skill for ", "add a domain to the fable method", or "give a lesser…
Cursor Skill (.mdc) Authoring
Author effective Cursor rules in .cursor/rules/.mdc - YAML frontmatter (description, globs, alwaysApply), the four rule types, scoped QA rules, subagents, and structure that actually steers the model.
fable-judge
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model…