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/avelino/mcp/copilot-instructionsgit clone --depth 1 https://github.com/avelino/mcpWhat 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 | $0.01616 | $0.01616 |
| Opus 5 | $0.00808 | $0.00808 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
mcp 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 yesterday.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions
Project Overview
mcp is a Rust CLI that turns MCP (Model Context Protocol) servers into terminal commands. It supports stdio and HTTP transports, a proxy/gateway mode, server registry, audit logging, and ACL-based auth.
Tech Stack
- Language: Rust (edition 2021)
- Async runtime: Tokio (full features)
- HTTP: Axum (server), Reqwest with rustls-tls (client)
- Serialization: Serde + serde_json
- Error handling:
anyhow::Resultthroughout - Storage: chrondb for persistent state
- Tests: built-in
#[cfg(test)]modules,tempfilefor test fixtures
Code Style & Conventions
- No
#[allow(dead_code)]— wire it up or delete it. - Functions do one thing. Max ~50 lines. Max 3 levels of nesting.
- Comments explain why, not what.
- No unnecessary abstractions — solve the actual problem, not a hypothetical one.
- Zero
unsafecode — all concurrency through safe abstractions.
Error Handling
- All functions return
anyhow::Result<T>. No custom error types. - Use
.context("msg")?or.with_context(|| format!("msg {var}"))?to add context on propagation. - Use
bail!("msg")for early returns with error. - Use
.map_err(|e| anyhow::anyhow!("msg: {e:?}"))only when wrapping external library errors that don't implementstd::error::Error. - Never silently swallow errors — at minimum log with
eprintln!.
Async Patterns
- All async via Tokio. Entry point is
#[tokio::main]. - Interior mutability with
Arc<Mutex<T>>orArc<RwLock<T>>for shared state across tasks. - Bounded
mpsc::channelfor task communication,oneshotfor request-response matching. tokio::spawnfor background tasks (readers, writers).spawn_blockingfor sync-heavy work (db writes).- Timeouts via
tokio::time::timeout(Duration, future)— never block indefinitely.
Serialization
- Derive order:
#[derive(Debug, Serialize, Deserialize, Clone)]. #[serde(rename = "camelCase")]for protocol fields matching JSON-RPC/MCP spec.#[serde(skip_serializing_if = "Option::is_none")]on allOptionfields for compact JSON.#[serde(default)]on optional deserialization fields.#[serde(untagged)]for config enums with variant ordering (serde tries in declaration order).
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.
- yesterday First seen · 142 lines · 1,616 tokens per session scan A c831901db5f3
mcp copilot-instructions.md is an instructions file published in the GitHub repository avelino/mcp (58 stars, last pushed 5d ago), licensed MIT. It adds 1,616 tokens to every session, about $0.0081 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.