synadia-agents CLAUDE.md

synadia-agents CLAUDE.md is an instructions file for Claude Code from synadia-ai/synadia-agents. It costs 4,187 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for working in the Synadia Agent Protocol repository, which contains software development kits, agent plugins, and example applications for NATS.

In plain words
What is it for?
Use it when changing the repository's SDKs, agent implementations, protocol-related code, documentation, or examples.
Why use it?
It helps an agent understand the repository layout, identify authoritative documentation, and avoid confusing protocol versions with package versions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

Install

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.

agentmods
npx agentmods add instructions/synadia-ai/synadia-agents/claude-md
Clone the repo
git clone --depth 1 https://github.com/synadia-ai/synadia-agents

Made for: Claude Code.

Wrote 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.

agentmods badge for synadia-agents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/synadia-ai/synadia-agents/claude-md.svg)](https://agentmods.dev/instructions/synadia-ai/synadia-agents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/synadia-ai/synadia-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/synadia-ai/synadia-agents/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,187 This file is loaded in full into every session.
When invoked 4,187 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04187 $0.04187
Opus 5 $0.02093 $0.02093
Sonnet 5 $0.00837 $0.00837
Haiku 4.5 $0.00419 $0.00419

Measured 6d ago against content hash b47088631998, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

synadia-agents CLAUDE.md 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 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.

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.

CLAUDE.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file orients Claude Code when working anywhere in this repo. For language-specific deep dives, defer to the package-level CLAUDE.md (e.g. client-sdk/python/CLAUDE.md) and to per-package READMEs.

What this repo is

The home for everything around the Synadia Agent Protocol for NATS — language SDKs that callers use, agent plugins that host the protocol, and example apps that exercise both. The root README.md covers the user-facing view: layout, subject namespace, wire shape, quickstart. Read it before making changes that touch user-visible surface.

The protocol spec is not vendored here. Canonical source: synadia-ai/synadia-agent-sdk-docs — always link to the GitHub URL when reasoning about wire shape. Local docs/protocol-mapping.md files inside each SDK translate spec → impl; they are not the spec itself.

Reference agents — canonical implementations

Every SDK in this repo ships a spec-compliant reference agent that implements the full §12 agent-checklist (service registration, prompt endpoint, status endpoint, heartbeats on agents.hb.*.*.*, terminator semantics). When reasoning about wire shape, expected on-the-wire behaviour, or testing a new SDK / agent, read these first — they are the authoritative on-the-wire counterpart to the spec doc.

  • TypeScript: agent-sdk/typescript/src/testing/reference-agent.ts — the ReferenceAgent class, importable from third-party packages via @synadia-ai/agent-service/testing (post-SDK-split — pre-split it lived under @synadia-ai/agents/testing). Runnable script: client-sdk/typescript/examples/_run-reference-agent.ts.
  • Python: agent-sdk/python/examples/_reference_agent.py — a runnable echo agent with conversation memory, used as the test harness for the numbered demos and as a wire-compat counterparty. (Moved with the host-side split into synadia-ai-agent-service; pre- split it lived under client-sdk/python/examples/.)

Read the full file on GitHub · 308 lines

Changes

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.

  1. 6d ago First seen · 308 lines · 4,187 tokens per session scan A b47088631998

Subscribe to this mod's changes

synadia-agents CLAUDE.md is an instructions file published in the GitHub repository synadia-ai/synadia-agents (77 stars, last pushed 4d ago), licensed Apache-2.0. It adds 4,187 tokens to every session, about $0.0209 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.