Borrowing it
Nothing to install: this file belongs to synadia-ai/synadia-agents-labs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/synadia-ai/synadia-agents-labs/main/CLAUDE.mdgit clone --depth 1 https://github.com/synadia-ai/synadia-agents-labsWrote 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/synadia-ai/synadia-agents-labs/claude-md)<a href="https://agentmods.dev/instructions/synadia-ai/synadia-agents-labs/claude-md"><img src="https://agentmods.dev/badge/instructions/synadia-ai/synadia-agents-labs/claude-md/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/instructions/synadia-ai/synadia-agents-labs/claude-md"><img src="https://agentmods.dev/badge/instructions/synadia-ai/synadia-agents-labs/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04100 | $0.04100 |
| Opus 5 | $0.02050 | $0.02050 |
| Sonnet 5 | $0.00820 | $0.00820 |
| Haiku 4.5 | $0.00410 | $0.00410 |
Grade A, and why
synadia-agents-labs 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 9d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Orientation for Claude Code (and any new contributor) working in this repo. Read this first; it assumes you know nothing about the project.
What this repo is
synadia-agents-labs is standalone courseware — small, runnable,
heavily-commented examples for the Synadia Agent Protocol for NATS SDKs. It
accompanies Synadia workshops and trainings, and doubles as a self-study ground.
It is deliberately independent of the SDK source: every example depends on
the published packages (@synadia-ai/agents + @synadia-ai/agent-service
from npm; synadia-ai-agents + synadia-ai-agent-service from PyPI). There is
no link back to the SDK monorepo — no file: deps, no submodules, no
relative imports into another repo. You can develop here without the SDK source
checked out.
- User-facing overview:
README.md— layout, conventions, the environment-variable reference, quickstart. Keep it in sync when you change user-visible surface. - The protocol spec (source of truth for wire shape) is not vendored: https://github.com/synadia-ai/synadia-agent-sdk-docs. Link to it; don't copy it.
- The SDK source lives in the separate
synadia-ai/synadia-agentsmonorepo. It's a reference, not a dependency. (On this machine it's typically a sibling dir:../synadia-agents.)
The protocol in 30 seconds
An agent is a NATS micro-service identified by a triple
<agent>/<owner>/<session> (e.g. echo/alice/main) — the SDK calls the 5th
subject token name in TypeScript and session_name in Python. From it the SDK
derives subjects:
agents.prompt.<agent>.<owner>.<name>— send a prompt, stream a replyagents.status.<agent>.<owner>.<name>— status endpointagents.hb.<agent>.<owner>.<name>— heartbeats (liveness)
A reply is a stream of typed frames: {"type":"status","data":"ack"} →
{"type":"response","data":"…"} (one or many) → an empty terminator.
Callers (@synadia-ai/agents) discover agents and prompt them; agents
(@synadia-ai/agent-service) host the endpoints. Wire protocol version is
0.3; the published package version is currently 0.5.2 (different axes —
don't conflate).
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.
- 9d ago First seen · 262 lines · 4,100 tokens per session scan A 7a27cd62ab45
synadia-agents-labs CLAUDE.md is an instructions file published in the GitHub repository synadia-ai/synadia-agents-labs (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 4,100 tokens to every session, about $0.0205 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.