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/shigechika/mcp-stdio/copilot-instructionsgit clone --depth 1 https://github.com/shigechika/mcp-stdioWrote 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/shigechika/mcp-stdio/copilot-instructions)<a href="https://agentmods.dev/instructions/shigechika/mcp-stdio/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shigechika/mcp-stdio/copilot-instructions.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 | $0.04193 | $0.04193 |
| Opus 5 | $0.02096 | $0.02096 |
| Sonnet 5 | $0.00839 | $0.00839 |
| Haiku 4.5 | $0.00419 | $0.00419 |
Grade A, and why
mcp-stdio copilot-instructions.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 3d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot code review instructions for mcp-stdio
Repository overview
mcp-stdio is a stdio-to-HTTP/SSE gateway/relay for the Model Context
Protocol. It translates between the stdio JSON-RPC framing that MCP hosts
(Claude Code, Claude Desktop, etc.) speak and the MCP HTTP transports
that remote servers expose:
- Streamable HTTP —
run()insrc/mcp_stdio/relay.py, speaking two protocol eras: 2025-06-18 (legacy, the default) and 2026-07-28 (modern, opt-in via--protocol-era modern|auto; era detected by aserver/discoverprobe). The modern era adds per-request_meta+Mcp-Method/Mcp-Nameheaders, no sessions, backgroundsubscriptions/listenstreams (includingresources/subscribeinterception), an MRTR bridge translatinginput_requiredresults into legacyelicitation/sampling/rootsround-trips, and a stdin reader thread that aborts the in-flight POST onnotifications/cancelled. - Legacy SSE (2024-11-05) —
run_sse()insrc/mcp_stdio/relay.py(--protocol-erais ignored there, with a warning)
This repo implements zero MCP tools of its own. There is no FastMCP, no
@mcp.tool() decorator, nothing that "wraps a tool return value" — do not
review this code as if it were an MCP tool server. It works in two
directions:
- relay (the original job,
relay.py) — faithfully relays a stdio stream to/from a remote HTTP endpoint (client side: stdin/stdout in, HTTP out), plus a full OAuth 2.1 client (oauth.py) and on-disk token cache (token_store.py) to authenticate against that endpoint. - serve (
server.py,mcp-stdio serve) — the mirror image (server side: HTTP in, stdio out): spawns a local stdio MCP server as a child process and publishes it as a Streamable HTTP endpoint so clients that can't spawn the server locally can reach it over the network. Dual-era on one endpoint:_request_era()classifies each POST conservatively (modern only on positive evidence —params._metacarries the protocolVersion key, or the method isserver/discover); legacy clients keep the sessioned per-child model unchanged, modern clients are served statelessly from a principal-keyedModernBackendPoolbehind a request-validation ladder. Stdlib-only (http.server+subprocess); optional layered auth (open / static bearer / embedded OAuth 2.1 authorization server). See Review focus §5 and §6.
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.
- 3d ago First seen · 303 lines · 4,193 tokens per session scan A 846bc8030138
mcp-stdio copilot-instructions.md is an instructions file published in the GitHub repository shigechika/mcp-stdio (8 stars, last pushed 11d ago), licensed MIT. It adds 4,193 tokens to every session, about $0.0210 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
Ruckus-vSZ-MCP AGENTS.md
AGENTS.md instructions for 0xEkho/Ruckus-vSZ-MCP, covering agents.md — ruckus vsz mcp server, vue d'ensemble du projet, agents disponibles, flux de travail pour une nouvelle fonctionnalité and canonical tool registry (52 tools — 12 modules).
Ruckus-vSZ-MCP copilot-instructions.md
Copilot instructions for 0xEkho/Ruckus-vSZ-MCP, covering copilot instructions — mcp template, quand invoquer les 4 agents (obligatoire), protocole de réponse and rappels mcp non négociables.
pi-anthropic-auth AGENTS.md
Instructions for gotgenes/pi-anthropic-auth, covering agents guide: pi-anthropic-auth, project, primary goal, current status and principles.
dario CLAUDE.md
Instructions for askalf/dario, covering dario — notes for claude code (and other llm coding agents), commits and prs, style, scope and when in doubt, ask.
pixiv-cli AGENTS.md
Instructions for FlanChanXwO/pixiv-cli, covering agents.md, 核心命令, 边界规则, 注意事项 and 文档路由.
sdk AGENTS.md
Instructions for zapier/sdk, covering agents.md, what this repo is, files to read before you start, when to use this sdk vs. alternatives and setup.