What is Shannon CLAUDE.md?

Repository guidance for working on Shannon, a distributed software platform built from Rust, Go, and Python services. It lists setup, run, testing, code-generation, and local Docker commands.

Use it to set up Shannon, start its development environment, run smoke and unit tests, regenerate protocol files, run CI checks, and build or start local Docker services.

It gives a coding agent the project context and the commands needed to develop and check changes across several programming languages and services.

How Kocoro-lab/Shannon configures Claude Code

About the project

Shannon is a framework for building and running production AI agents that coordinate multiple agents through different execution strategies. It is used by teams that need agent collaboration, token budgets, human approvals, sandboxed code execution, and visibility into agent runs. The catalogue instruction supports working with Shannon.

Kocoro-lab/Shannon · 2,314 stars · on GitHub · shannon.run

Reuse

Borrowing it

Nothing to install: this file belongs to Kocoro-lab/Shannon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Kocoro-lab/Shannon/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Kocoro-lab/Shannon

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kocoro-lab/shannon/claude-md/github.svg)](https://agentmods.dev/instructions/kocoro-lab/shannon/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kocoro-lab/shannon/claude-md"><img src="https://agentmods.dev/badge/instructions/kocoro-lab/shannon/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kocoro-lab/shannon/claude-md"><img src="https://agentmods.dev/badge/instructions/kocoro-lab/shannon/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,717 This file is loaded in full into every session.

When invoked 1,717 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01717	$0.01717
Opus 5.5	$0.00687	$0.00687
Sonnet 5.5	$0.00343	$0.00343
Haiku 4.5	$0.00172	$0.00172

Measured 2mo ago against content hash 36f0b66a8d18, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Shannon CLAUDE.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 2mo 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 -sS -X POST http://localhost:8080/api/v1/tasks \

CLAUDE.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 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 code in this repository.

Project Overview

Shannon is an open-source, enterprise-grade multi-agent AI platform that combines Rust (agent core), Go (orchestration with Temporal), and Python (LLM services) to create a token-efficient, distributed AI system.

Essential Commands

# Setup & Run
make setup && vim .env && make dev         # Setup, configure API keys, start all
make smoke                                # E2E smoke tests
make proto                                # Regenerate proto files after .proto changes
make ci                                   # Run CI checks

# Local Docker Builds
# Pattern: docker build --no-cache -f <Dockerfile> -t <image> .
# Then: docker compose -f deploy/compose/docker-compose.yml up -d <service> --no-build
# Dockerfiles: go/orchestrator/Dockerfile, go/orchestrator/cmd/gateway/Dockerfile,
#              python/llm-service/Dockerfile, rust/agent-core/Dockerfile

# Unit Tests
cd rust/agent-core && cargo test
cd go/orchestrator && go test -race ./...
cd python/llm-service && python3 -m pytest

Project Structure

rust/agent-core/: Enforcement gateway, WASI sandbox, gRPC server
go/orchestrator/: Temporal workflows, budget manager, complexity analyzer
python/llm-service/: LLM providers, MCP tools, agent loop
protos/: Shared protocol buffer definitions
deploy/compose/: Docker Compose configuration
config/: Hot-reload configuration files
docs/: Architecture and API documentation
scripts/: Automation and helper scripts

API Endpoints (4 Entry Points)

Endpoint	Orchestrator?	Format	Use Case
`POST /v1/chat/completions`	Yes	OpenAI-compatible	Apps using OpenAI SDK -- auto tool selection, deep research, swarm, strategies
`POST /v1/completions`	No (Proxy)	OpenAI-compatible	Thin LLM proxy -- single call, no orchestration, caller-supplied tools only
`POST /api/v1/tasks`	Yes	Shannon native (sync)	Full orchestrator pipeline, sync response
`POST /api/v1/tasks/stream`	Yes	Shannon native (SSE)	Full orchestrator pipeline, streaming SSE events

Read the full file on GitHub · 166 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.

2mo ago First seen · 166 lines · 1,717 tokens per session scan A 36f0b66a8d18

Subscribe to this mod's changes

Shannon CLAUDE.md is an instructions file published in the GitHub repository Kocoro-lab/Shannon (2,314 stars, last pushed 2mo ago), licensed MIT. It adds 1,717 tokens to every session, about $0.0069 per session on Opus 5.5. 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 2026-08-30.

agent ai multi-agent-systems

Shannon CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Shannon CLAUDE.mdKocoro-lab/Shannon	Instructions file	2.3k	2mo ago	MIT	A	1,717	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Shannon: Instructions file for Claude Code