Borrowing it
Nothing to install: this file belongs to shigechika/mcp-stdio. 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/shigechika/mcp-stdio/main/.github/copilot-instructions.mdgit 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/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/shigechika/mcp-stdio/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shigechika/mcp-stdio/copilot-instructions.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 | $0.04193 | $0.04193 |
| Opus 5.5 | $0.01677 | $0.01677 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (9 stars, last pushed yesterday), licensed MIT. It adds 4,193 tokens to every session, about $0.0168 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.