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/jcbmrrs/agent-mesh-core/agents-mdgit clone --depth 1 https://github.com/jcbmrrs/agent-mesh-coreWrote 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/jcbmrrs/agent-mesh-core/agents-md)<a href="https://agentmods.dev/instructions/jcbmrrs/agent-mesh-core/agents-md"><img src="https://agentmods.dev/badge/instructions/jcbmrrs/agent-mesh-core/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 5.1 | $0.06611 | $0.06611 |
| Opus 5 | $0.03306 | $0.03306 |
| Sonnet 5 | $0.01322 | $0.01322 |
| Haiku 4.5 | $0.00661 | $0.00661 |
Grade A, and why
agent-mesh-core 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 4d 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 — 127 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.
Repository status
This repository now contains the implemented agent-mesh-core Python package, tests, deployment helpers, and documentation. Use README.md for user-facing setup/onboarding, docs/OPERATIONS.md for Mac mini service operation, and docs/ROADMAP.md for current task tracking. docs/IMPLEMENTATION_PLAN_v2.md remains the concrete design/build plan and invariant reference. docs/archive/ holds the original design drafts (BACKGROUND.md, MULTI-AGENT-GUIDE.md, PROMPT.md, PROJECT-SETUP.md) for historical/rationale value only — they describe an earlier, superseded SMB-mount transport (see "Architecture decision" below) and should never be implemented literally.
Repository visibility: public since 2026-07-23
This repository is public on GitHub (jcbmrrs/agent-mesh-core), not a private working repo. docs/ROADMAP.md's completed TASK-14 did the one-time release pass (LICENSE, SECURITY.md, placeholder-style docs, personal-path scrub). That pass is done, but public visibility is now a standing property of the repo, not a one-off checklist — every subsequent change that touches docs, commit messages, or config needs the same scrutiny applied before it's pushed, not as a follow-up cleanup pass.
Before pushing any new commit that adds or edits docs, comments, config, or examples, check it for:
- Real internal network details — Tailscale/LAN IPs, internal hostnames, VPN/tailnet names. Use a placeholder matching the existing style (
<mac-mini-tailscale-ip>,<mac-mini-tailscale-host>) instead of a literal address, the same wayREADME.mdanddocs/OPERATIONS.mdalready do. - Credentials or tokens of any kind — API keys, passwords, auth tokens,
.envcontents. These never belong in this repo regardless of visibility; public makes the cost of a mistake immediate instead of merely bad practice. - Other people's personal data — names, emails, or identifying details belonging to anyone other than Jacob. Not expected to come up in a single-operator project, but check example configs and test fixtures for accidentally-realistic data before assuming otherwise.
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.
- 4d ago First seen · 127 lines · 6,611 tokens per session scan A ff0170c06ffd
agent-mesh-core AGENTS.md is an instructions file published in the GitHub repository jcbmrrs/agent-mesh-core (0 stars, last pushed 1mo ago), licensed MIT. It adds 6,611 tokens to every session, about $0.0331 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.
Other instructions, from other repositories
Avernet AGENTS.md
AGENTS.md instructions for inclusionAI/Avernet, covering agents.md, source of truth, project overview, repository layout and module responsibilities.
brain-in-the-fish CLAUDE.md
Instructions for fabio-rovai/brain-in-the-fish, covering brain in the fish, relationship to open-ontologies, module overview, pipeline and mcp tools.
statewave-multi-agent-shared-context AGENTS.md
Instructions for smaramwbc/statewave-multi-agent-shared-context, covering statewave project memory, read it first and persist durable facts.
gemot CLAUDE.md
Claude Code instructions for justinstimatze/gemot, covering gemot, key commands and architecture.
coordinate-agents AGENTS.md
AGENTS.md instructions for hogancv/coordinate-agents, covering repository instructions for ai contributors, canonical identity, repository map, required checks and change rules.
SuperAgenticMCP AGENTS.md
AGENTS.md instructions for ANAMIZED/SuperAgenticMCP, covering agents.md — superagenticmcp, what this project is, how to run & verify, hard rules for agents and surfaces that must stay working.