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 instructions/growthxai/output/claude-mdgit clone --depth 1 https://github.com/growthxai/outputWrote 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/instructions/growthxai/output/claude-md)<a href="https://agentmods.dev/instructions/growthxai/output/claude-md"><img src="https://agentmods.dev/badge/instructions/growthxai/output/claude-md.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 5.1 | $0.01185 | $0.01185 |
| Opus 5 | $0.00593 | $0.00593 |
| Sonnet 5 | $0.00237 | $0.00237 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade B, and why
output CLAUDE.md scanned grade B with 2 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 6d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- And from a separate terminal, run `curl -X POST http://localhost:3001/workflow -H "Content-Type: application/json" -d '{"workflowName": "simple", "input": {"values": [1, 2, 3, 4, 5]}}'` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- And from a separate terminal, run `curl -X POST http://localhost:3001/workflow -H "Content-Type: application/json" -d '{"workflowName": "simple", "input": {"values": [1, 2, 3, 4, 5]}}'` How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with the Output.ai (often referred as just Output) framework codebase.
Project Overview
Output.ai is an AI framework for building reliable production-ready LLM workflows & agents. It contains multiple NPM packages and supporting infrastructure with best AI engineering practices baked-in. Under the hood, the Output framework uses Temporal.io as the execution layer.
Documentation References
- Project setup & commands: See README.md
- Workflow structure & examples: See README.md#workflow-structure
- Framework packages:
- Core: sdk/core/README.md
- LLM: sdk/llm/README.md
- HTTP: sdk/http/README.md
- Credentials: sdk/credentials/README.md
- Evals: sdk/evals/README.md
- Framework: sdk/framework/README.md
- CLI: sdk/cli/README.md
- Test examples: See test_workflows/ directory
Tech Stack Context
- Runtime: Node.js >=24.15.0
- Workflow orchestration: Temporal
- LLM providers: Anthropic, OpenAI (via AI SDK)
- Testing: Vitest
- Containerization: Docker Compose
Environment Variables
Configuration is documented in:
- Root environment: README.md#env-file
- Workflow secrets: Required in
test_workflows/.env
Package Management
This monorepo uses pnpm workspaces with a pnpm-workspace.yaml and pnpm-lock.yaml.
Note: the pnpm convention applies to this monorepo only. Projects generated by output init are npm-based — sdk/cli/src/templates/project/package.json.template ships npm scripts (output:worker:build, output:worker:watch, output:dev). When editing CLI templates or the coding_assistants/ plugin docs, write the template's npm commands, not monorepo-only ones like pnpm run build:packages.
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.
- 6d ago First seen · 95 lines · 1,185 tokens per session scan B 5ba0aa848685
output CLAUDE.md is an instructions file published in the GitHub repository growthxai/output (435 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,185 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
oxc AGENTS.md
AGENTS.md instructions for oxc-project/oxc, covering agents.md - ai assistant guide for oxc, ai usage policy for contributors, repository structure, core crates and development commands.
agentos CLAUDE.md
Claude Code instructions for rivet-dev/agentos, covering agentos, boundaries, security model, sqlite schema ownership and runtime and registry.
langgraphjs AGENTS.md
AGENTS.md instructions for langchain-ai/langgraphjs, covering repository instructions and corridor security analysis.
intlayer CLAUDE.md
Claude Code instructions for aymericzip/intlayer, covering repo layout, commands (run from root), content declaration flow, git and commit conventions.
opengeni AGENTS.md
AGENTS.md instructions for Cloudgeni-ai/opengeni, covering agent / automation notes (opengeni), full local stack, architecture notes, pull-request delivery across moving main and keeping these notes current.
stardrive AGENTS.md
AGENTS.md instructions for peltmonger/stardrive, covering 🛑 critical: repository bootstrap directive 🛑, general information and guidelines for ai agents, analyze your high-level use case first, how the .ai guidance files relate and this is an astro project.