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/uninen/devserver-mcp/copilot-instructionsgit clone --depth 1 https://github.com/Uninen/devserver-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 | $0.00689 | $0.00689 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
devserver-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.
Copies of this mod
2 near-identical copies found in the catalogue:
- devserver-mcp CLAUDE.md — 100% identical, 0 lines differ
- devserver-mcp GEMINI.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Project: Devserver MCP
This project is a Model Context Protocol (MCP) server that manages development servers (Django, Vue, Celery, etc.) for LLM-assisted development workflows. Provides programmatic control over multiple development servers through a unified interface with a beautiful TUI.
Quick Reference
- Dependency and environment management:
uvuv add [package]-- add dependencyuv add --dev [package]-- add dev dependencyuv run [command in .venv context]-- run a command in the project environmentpyproject.toml-- Python project configuration
- Tests:
- Run with: use your
run_teststool oruv run pytest - In
tests/
- Run with: use your
- Use Ruff for linting and formatting:
uv run ruff check --fix path/to/file.py-- fix all fixable linting errorsuv run ruff format path/to/file.py-- format
- Test the server implementation using the test app (see details below):
uv run devservers
Coding Guidelines
- Python 3.13+, type hints, PEP 8
- Handle errors explicitly
- Never add any comments or doctsrings unless asked to
- Always follow security best practices. Never introduce code that exposes or logs secrets and keys
- Always lint and format all the code you write using Ruff
Testing Guidelines
- Adhere to the general testing guidelines in
docs/writing_tests.md - Write meaningful tests, not coverage fillers
- Always use pytest functions, never use classes
- When creating or fixing tests, always run the full test suite to make sure all tests pass
Test App Structure
testapp/
├── front/ # simple Vite app
└── backend.py # simple FastAPI app
devservers.yml # Test configuration
Documentation
- See
docs/design.mdfor technical design specs - See latest FastMCP documentation at: https://gofastmcp.com/llms-full.txt
- Check existing code patterns before implementing new features
- Textual documentation: https://textual.textualize.io/guide/
Change Logging
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 · 60 lines · 689 tokens per session scan A e00841d8f444
devserver-mcp copilot-instructions.md is an instructions file published in the GitHub repository Uninen/devserver-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 689 tokens to every session, about $0.0034 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
playwright CLAUDE.md
Instructions for microsoft/playwright, covering monorepo packages, browser packages, tooling packages, key directories and build.
playwright-cli CLAUDE.md
Instructions for microsoft/playwright-cli, covering commit convention, ... make changes .. and summary.
playwriter AGENTS.md
Instructions for remorses/playwriter, covering backward compatibility, architecture, development, running mcp locally and running cli locally.
cli AGENTS.md
Instructions for qawolf/cli, covering @qawolf/cli — agent instructions, commands, testing, project structure and code style.
grok-register-panel AGENTS.md
Instructions for lij768423-svg/grok-register-panel, covering agents.md, project scope, architecture and ownership, runtime flows and setup and run.
dev-browser AGENTS.md
Instructions for SawyerHood/dev-browser, covering claude.md, tooling and validation.