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/wiztheagent/ironmesh/agents-mdgit clone --depth 1 https://github.com/WizTheAgent/IronMeshWrote 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/wiztheagent/ironmesh/agents-md)<a href="https://agentmods.dev/instructions/wiztheagent/ironmesh/agents-md"><img src="https://agentmods.dev/badge/instructions/wiztheagent/ironmesh/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 | $0.01853 | $0.01853 |
| Opus 5 | $0.00927 | $0.00927 |
| Sonnet 5 | $0.00371 | $0.00371 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
IronMesh AGENTS.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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide for this repository
This file tells AI coding assistants (Claude Code, Cursor, Aider, Zed,
Codex, and similar) how to operate productively in the IronMesh
codebase. It is the emerging community convention for
repo-level AI guidance. Human contributors should read CONTRIBUTING.md.
What IronMesh is
A local-first, end-to-end encrypted agent-to-agent mesh protocol.
Python daemon + TypeScript client + 25 MCP tools. No cloud
dependencies. See README.md for the product-level summary.
Quick repo orientation
ironmesh/ # main Python package
├── bridge.py # daemon core — server + lifecycle (composes the mixins below)
├── handshake.py # client handshake + outbound connect + rekey
├── routing.py # inbound dispatch + outbound send pipeline
├── trust_ops.py # revocation + pending-trust gate + TOFU check
├── ratelimit.py # auth-failure lockout + bandwidth throttle
├── metrics.py # counters + Prometheus/JSON exposition
├── dashboard.py # GUI HTTP/WebSocket server + operator commands
├── dashboard_html.py # embedded dashboard page (GUI_HTML)
├── trust.py # TOFU pin store + capability-set binding
├── audit.py # HMAC-chained audit log + cross-process flock
├── mesh.py # distance-vector router + DedupCache
├── crypto.py # thin wrapper over PyNaCl primitives
├── protocol.py # binary frame + JSON-dispatch decoders
├── capabilities.py # local + remote capability registries
├── cli.py # `ironmesh` command surface
├── telemetry.py # OpenTelemetry shim (lazy, no-op on vanilla)
└── keys.py # Ed25519 identity: generate / save / load
ironmesh_mcp/ # MCP server (Claude Desktop / Claude Code)
clients/ts/ # TypeScript client — `@wiztheagent/ironmesh-client`
tests/ # pytest suite — unit + property + concurrency
docs/ # public-facing docs (shipped with the release)
scripts/ # release-smoke, leak-scan, stress harness
examples/ # runnable walkthroughs (cap_binding_workflow etc.)
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.
- 5d ago First seen · 155 lines · 1,853 tokens per session scan A d496d5d22c3c
IronMesh AGENTS.md is an instructions file published in the GitHub repository WizTheAgent/IronMesh (22 stars, last pushed 16d ago), licensed MIT. It adds 1,853 tokens to every session, about $0.0093 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
prime-silo CLAUDE.md
Claude Code instructions for binary16labs/prime-silo, covering prime-silo agent navigation, current status (as of 2026-07-16), architecture in one sentence, what agents need to know and 1. agent authority (strict boundaries).
prime-silo AGENTS.md
AGENTS.md instructions for binary16labs/prime-silo, covering agents, documentation first, agents file index, programming guide and top-level structure.
a2amesh AGENTS.md
AGENTS.md instructions for oaslananka/a2amesh, covering a2a mesh agent map, what this repository is, setup, build and test and repository layout.
agent-meet CLAUDE.md
Instructions for matanrak/agent-meet, covering agent-meet development guidelines, active technologies, project structure, commands and code style.
agentic-commerce-skills-plugins GEMINI.md
Instructions for OrcaQubits/agentic-commerce-skills-plugins, covering ucp-agentic-commerce, important: live documentation rule, official sources (fetch these before implementation), ucp conceptual architecture and four roles.
codex-a2a-gateway AGENTS.md
AGENTS.md instructions for phamviet86/codex-a2a-gateway, covering repository guidance, mission and scope, architecture ownership, non-negotiable invariants and compatibility policy.