What is myrmex-hive CLAUDE.md?

Repository instructions for Myrmex Hive, a Go system for securely managing remote edge servers through a central gateway. Edge servers are remote machines, and the gateway is the central connection point.

They guide building and validating the agent, gateway, and operator command-line tool, generating test keys, running local services, and executing integration tests.

They explain the system layout, preferred commands, testing process, and security model so changes fit the existing architecture.

How olafkfreund/myrmex-hive configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to olafkfreund/myrmex-hive. 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/olafkfreund/myrmex-hive/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/olafkfreund/myrmex-hive

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/olafkfreund/myrmex-hive/claude-md/github.svg)](https://agentmods.dev/instructions/olafkfreund/myrmex-hive/claude-md)

Your own site

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

Per session 2,361 This file is loaded in full into every session.

When invoked 2,361 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.02361	$0.02361
Opus 5	$0.01180	$0.01180
Sonnet 5	$0.00472	$0.00472
Haiku 4.5	$0.00236	$0.00236

Measured 8d ago against content hash 16efc6dd1f3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

myrmex-hive 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 8d 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 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.

What this is

Myrmex Hive (github.com/olafkfreund/myrmex-hive) is a Go implementation of the Model Context Protocol (MCP) for securely managing distributed edge servers with zero inbound ports on the targets. Agents dial out to a central Gateway over SSH; operators reach the Gateway (never the agents) via CLI, MCP, or REST. A local LLM (Ollama/Gemma) orchestrates multi-step actions.

Three binaries from cmd/: agent (runs on targets), gateway (central hub), myrmex (operator CLI).

Commands

Prefer the Justfile recipes:

just build — builds all three binaries into bin/
just validate — go vet ./... + go fmt ./... (CI runs both; keep the tree fmt-clean)
just test — go test -v ./...
just run-gateway / just run-agent — build then run locally against gateway_config.json / agent_config.json
just generate-keys — generate Ed25519 keys for local testing (generate_keys.sh)
just docker-test — setup_test_env.sh then go run cmd/integration-test/main.go (spins up the compose stack and drives it end-to-end)
just clean — removes bin/, generated keys, and test_env/

Run one package's tests or a single test:

go test -v ./pkg/command/           # a package
go test -v -run TestName ./cmd/gateway/

The security-critical layers are covered: pkg/command (allowlist + no-shell execution, ~97%), pkg/audit (signature/chain tamper detection), cmd/agent's host-key verification and tool-arg validation, and the gateway's auth/redaction/OIDC paths. Still untested (lower value): cmd/myrmex (CLI glue) and pkg/metrics (OS introspection).

Nix (CI builds via Nix, so flake changes must pass): nix build, nix flake check, nix run .#myrmex -- --help. nix develop gives a shell with go, just, docker-compose.

Ollama side-services for the LLM: docker compose --profile ollama-cpu up -d (or ollama-gpu, needs NVIDIA toolkit), preloaded with gemma4:e4b.

Read the full file on GitHub · 70 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.

8d ago First seen · 70 lines · 2,361 tokens per session scan A 16efc6dd1f3c

Subscribe to this mod's changes

myrmex-hive CLAUDE.md is an instructions file published in the GitHub repository olafkfreund/myrmex-hive (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,361 tokens to every session, about $0.0118 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 2026-08-31.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

myrmex-hive: Instructions file for Claude Code