pcp-mcp copilot-instructions.md

pcp-mcp copilot-instructions.md is an instructions file for GitHub Copilot from major/pcp-mcp. It costs 931 tokens per session, scanned A, original, MIT.

A set of GitHub Copilot instructions for reviewing code in the pcp-mcp project. It tells the reviewer to look for ways code could fail, including edge cases, production problems, maintenance issues, and security holes.

In plain words
What is it for?
Reviewing pcp-mcp source files, tests, and related changes against the project's Python stack, design decisions, and failure-focused checklists.
Why use it?
It gives code reviews a consistent focus on preventing failures instead of only judging whether code looks good.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/major/pcp-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/major/pcp-mcp

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for pcp-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/major/pcp-mcp/copilot-instructions.svg)](https://agentmods.dev/instructions/major/pcp-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/major/pcp-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/major/pcp-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 931 This file is loaded in full into every session.
When invoked 931 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00931 $0.00931
Opus 5 $0.00465 $0.00465
Sonnet 5 $0.00186 $0.00186
Haiku 4.5 $0.00093 $0.00093

Measured 3d ago against content hash 10efcdaef5e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pcp-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 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.

.github/copilot-instructions.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Code Review Instructions

Review Philosophy: Invert, Always Invert

Apply Charlie Munger's inversion principle: Instead of asking "Is this code good?", ask "What would make this code fail?"

Focus on preventing failure rather than achieving brilliance:

  • What edge cases would break this?
  • What would cause this to fail in production?
  • What would make this unmaintainable in 6 months?
  • What security holes does this open?

When something could fail, explain HOW it would fail and suggest the prevention.


Project Context: pcp-mcp

MCP (Model Context Protocol) server for Performance Co-Pilot (PCP). Python 3.10+, FastMCP 3.1+.

Tech Stack

  • MCP Framework: FastMCP 3.1+
  • HTTP Client: httpx (async)
  • Backend: pmproxy REST API
  • Type checking: ty
  • Linting/Formatting: ruff
  • Testing: pytest + pytest-asyncio + respx
  • Package manager: uv

Key Design Decisions

  • Clumped tools (get_system_snapshot) instead of per-metric tools
  • Client-side rate calculation for counter metrics
  • Configurable target_host for remote monitoring
  • Pydantic response models with assessment fields

Inversion Checklists by File Type

Source Code (src/pcp_mcp/**/*.py)

MCP server failures to prevent:

  • Tools not returning proper Pydantic response models
  • Not handling httpx exceptions (must convert to ToolError)
  • Blocking calls in async tool functions
  • Missing type hints or docstrings
  • Rate calculation errors (counter vs gauge metrics)

FastMCP patterns to enforce:

  • Tools use @mcp.tool() decorator with proper type hints
  • Resources use @mcp.resource() decorator
  • Context accessed via ctx.request_context.lifespan_context
  • Errors raised as ToolError or ResourceError

Client (src/pcp_mcp/client.py)

What would cause the client to fail?

  • Not creating pmapi context on __aenter__
  • Not closing httpx client on __aexit__
  • Rate calculation with wrong elapsed time
  • Not handling counter wrap-around
  • Timeout not respected

Read the full file on GitHub · 121 lines

Changes

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.

  1. 3d ago First seen · 121 lines · 931 tokens per session scan A 10efcdaef5e3

Subscribe to this mod's changes

pcp-mcp copilot-instructions.md is an instructions file published in the GitHub repository major/pcp-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 931 tokens to every session, about $0.0047 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens