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/npow/claude-relay/agents-mdgit clone --depth 1 https://github.com/npow/claude-relayWrote 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/npow/claude-relay/agents-md)<a href="https://agentmods.dev/instructions/npow/claude-relay/agents-md"><img src="https://agentmods.dev/badge/instructions/npow/claude-relay/agents-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 | $0.00849 | $0.00849 |
| Opus 5 | $0.00425 | $0.00425 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
claude-relay AGENTS.md 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**curl:** How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agent Relay
What this is
Drop-in OpenAI & Anthropic API-compatible server that routes requests through claude -p CLI.
Quick setup
Prerequisites: claude CLI installed and on PATH, Python 3.10+, uv
# Install and run
uvx agent-relay serve
# Or from source
git clone https://github.com/npow/claude-relay.git
cd claude-relay && uv sync && uv run agent-relay serve
Default: http://0.0.0.0:8082. Override with --host / --port.
Configuring clients
OpenAI SDK (Python):
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8082/v1", api_key="unused")
response = client.chat.completions.create(
model="sonnet", messages=[{"role": "user", "content": "Hello"}], stream=True
)
Anthropic SDK (Python):
from anthropic import Anthropic
client = Anthropic(base_url="http://localhost:8082", api_key="unused")
response = client.messages.create(
model="sonnet", max_tokens=1024, messages=[{"role": "user", "content": "Hello"}]
)
LangChain:
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(base_url="http://localhost:8082/v1", api_key="unused", model="sonnet")
curl:
curl http://localhost:8082/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model":"sonnet","messages":[{"role":"user","content":"Hello"}]}'
API endpoints
| Method | Path | Description |
|---|---|---|
| GET | /health |
Server + CLI status |
| GET | /v1/models |
List available models |
| POST | /v1/chat/completions |
OpenAI-compatible chat |
| POST | /v1/messages |
Anthropic-compatible messages |
All endpoints also available without /v1 prefix (e.g. /models, /chat/completions, /messages).
Models
| Model | Notes |
|---|---|
opus |
Most capable |
sonnet |
Default if omitted |
haiku |
Fastest |
Passed directly to claude --model.
Ignored parameters
These are silently discarded — Claude Code CLI does not expose them:
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.
- 4d ago First seen · 112 lines · 849 tokens per session scan A e89653ab69c1
claude-relay AGENTS.md is an instructions file published in the GitHub repository npow/claude-relay (6 stars, last pushed 3mo ago), licensed MIT. It adds 849 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
helix AGENTS.md
AGENTS.md instructions for helixml/helix, a project described as: ♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️.
helix CLAUDE.md
Claude Code instructions for helixml/helix, covering helix development rules, communication style, forbidden actions, git and filesystem.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
open-swe CLAUDE.md
Claude Code instructions for langchain-ai/open-swe, a project described as: An Open-Source Asynchronous Coding Agent.
open-multi-agent AGENTS.md
AGENTS.md instructions for open-multi-agent/open-multi-agent, covering agents.md, repository map, commands, working rules and validation by change type.
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.