Borrowing it
Nothing to install: this file belongs to symphos-ai/orcho-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/symphos-ai/orcho-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/symphos-ai/orcho-mcpWrote 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/symphos-ai/orcho-mcp/agents-md)<a href="https://agentmods.dev/instructions/symphos-ai/orcho-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/symphos-ai/orcho-mcp/agents-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.
<a href="https://agentmods.dev/instructions/symphos-ai/orcho-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/symphos-ai/orcho-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01297 | $0.01297 |
| Opus 5 | $0.00648 | $0.00648 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
orcho-mcp 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 9d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orcho-mcp Instructions
Scope
This file applies to orcho-mcp/.
orcho-mcp is the Apache-2.0 public Model Context Protocol server. It exposes
orcho-core to Claude Code, Cursor, Zed, and other MCP-speaking
clients.
Also obey the workspace-level ../AGENTS.md.
Local Instruction Files
More specific instructions live near the code they govern:
docs/AGENTS.md— public documentation style and canonical doc ownership.tests/AGENTS.md— test layer rules, fixtures, and architecture contracts.src/orcho_mcp/AGENTS.md— source package boundaries and adapter rules.src/orcho_mcp/supervisor/AGENTS.md— subprocess lifecycle invariants.
Workspace Development Pipeline
When working on this repo inside the Orcho workspace, follow
../DEVELOPMENT_PIPELINE.md. That manual pipeline governs direct source
development only; it is separate from Orcho-managed worktree runs.
Stable Install Is Read-Only
Stable Orcho is a pipx install (venv at $HOME/.local/pipx/venvs/orcho,
shims in $HOME/.local/bin). Do not edit files inside that venv directly.
Change the canonical workspace repos and promote with orcho-promote; touch
the stable install only when the user explicitly asks to debug or repair it.
Build, Run, And Test
pip install -e ".[dev]"
pytest
pytest -m mcp_integration
orcho-mcp
python -m orcho_mcp
The default pytest suite covers L1 unit, L2 registration, and L3 stdio E2E.
The mcp_integration marker runs slower L4 subprocess and --mock pipeline
coverage.
Use python -m orcho_mcp in tests and smoke checks when reproducibility across
pip-install state matters.
Test Methodology
Use the four-layer test pyramid. Each layer catches a different class of bug:
| Layer | What | Catches | Misses |
|---|---|---|---|
| L1 pure unit | Call @mcp.tool handlers as plain Python functions with synthetic fixtures |
Business logic, edge cases, error mapping, Pydantic round-trip | stdio, registration, capability negotiation, dual-import |
| L2 server registration | In-process await mcp.list_tools() against the FastMCP instance |
Dual-import bugs, missed imports, JSON Schema generation failures | Wire format, stdio purity |
| L3 stdio E2E | Subprocess plus mcp.client.stdio.stdio_client, ClientSession.initialize(), call_tool, list_resources, list_prompts |
stdout pollution, capability negotiation, JSON-RPC framing | Pipeline lifecycle |
| L4 mock integration | Real subprocess pipeline through Orcho's --mock provider |
Subprocess lifecycle, watch/progress notifications, race conditions | — |
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.
- 9d ago First seen · 132 lines · 1,297 tokens per session scan A b18a5d230121
orcho-mcp AGENTS.md is an instructions file published in the GitHub repository symphos-ai/orcho-mcp (4 stars, last pushed today), licensed Apache-2.0. It adds 1,297 tokens to every session, about $0.0065 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
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.