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/breetygreen/myco/agents-mdgit clone --depth 1 https://github.com/BreetyGreen/MycoWrote 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/breetygreen/myco/agents-md)<a href="https://agentmods.dev/instructions/breetygreen/myco/agents-md"><img src="https://agentmods.dev/badge/instructions/breetygreen/myco/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 | $0.01924 | $0.01924 |
| Opus 5 | $0.00962 | $0.00962 |
| Sonnet 5 | $0.00385 | $0.00385 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
Myco 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — orientation for AI agents & contributors
This file is read automatically by Codex CLI (and often symlinked to
CLAUDE.md). It's the fastest way for an AI agent — or a human — to get oriented after a freshgit clone, on a brand-new machine, and continue the work. Keep it short and factual.
What this project is
Myco — "the mycelial layer for your AI agents." A self-contained macOS
menu-bar app that connects the AI coding agents on your Mac so they can share
skills, hand off conversations, and unify history. The repo
directory is still named multi-agent-skill-sharing/ for historical reasons;
the product is Myco.
Three capabilities, all read-only toward the agents (Myco never writes back into any agent's storage):
- Share skills — fan one
SKILL.mdout to each agent's repo skill dir. - Relay conversations — package one chat as paste-ready text to continue in another agent, in a legitimately new session (no forged IDs, no DB writes).
- Unify history — read every agent's local transcripts into one neutral, searchable, offline timeline.
Architecture (two layers)
| Layer | Where | What |
|---|---|---|
| App — macOS | app/Sources/Myco/ |
SwiftUI + AppKit menu-bar app (NSStatusItem + NSPopover). Builds with Command Line Tools only — no Xcode. |
| App — Windows | app-windows/ |
WPF tray app (WinForms NotifyIcon + WPF panel, zero NuGet deps). Builds with the .NET 8 SDK (dotnet build). |
| Engine (the brains) | engine/ |
Pure Python-stdlib CLIs both apps call via Process. No third-party deps. |
The native apps are thin shells; all real work (detection, distribution, chat
parsing, handoff) lives in the Python engine. The installed macOS .app
bundles the engine into Contents/Resources/engine/ and uses macOS's own
python3; the Windows zip ships the engine next to Myco.exe plus an
embedded python.org Python — both fully self-contained. On Windows, agent
detection also runs in the engine (agent_status.py --json) rather than being
reimplemented in C#.
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 · 148 lines · 1,924 tokens per session scan A 428d2b5f08ee
Myco AGENTS.md is an instructions file published in the GitHub repository BreetyGreen/Myco (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,924 tokens to every session, about $0.0096 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
claude-code-templates CLAUDE.md
Claude Code instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
x-dev-pipeline CLAUDE.md
Instructions for KtKID/x-dev-pipeline, covering claude.md, 仓库性质, 仓库布局, 核心管线 and skill 间契约（改 skill 前必读）.
superpipelines AGENTS.md
AGENTS.md instructions for gustavo-meilus/superpipelines, covering superpipelines agent onboarding, project purpose, stack and runtime, build, test, run and architecture map.
cortex-memory CLAUDE.md
Instructions for SKULLFIRE07/cortex-memory, covering cortex, project overview, architecture, build and key design decisions.
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).
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.