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/call518/mcp-openstack-ops/copilot-instructionsgit clone --depth 1 https://github.com/call518/MCP-OpenStack-OpsWhat 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 | $0.01488 | $0.01488 |
| Opus 5 | $0.00744 | $0.00744 |
| Sonnet 5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
MCP-OpenStack-Ops copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ measured 2d 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 โ 154 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions
๐ซ CRITICAL RESTRICTIONS - ALWAYS ENFORCE
Never Execute These Operations Directly:
- Git operations: Never run
git add,git commit,git push,git pull,git tag, or any Git commands - Docker operations: Never run
docker build,docker run,docker-compose up/down,docker push, or any Docker commands - Instead: Always ask the user to execute these commands manually
Python Execution Requirements:
- MANDATORY: Always use
.venv/bin/pythonfor all Python execution - MANDATORY: Always use
.venv/bin/pipfor all package management - NEVER use:
python,python3,/usr/bin/python,pip,pip3, or system Python/pip - Example: Use
.venv/bin/python -m mcp_openstack_opsinstead ofpython -m mcp_openstack_ops - Example: Use
.venv/bin/pip install packageinstead ofpip install package
MCP Tool Safety Control Requirements:
- MANDATORY: When adding new MCP tools with modify operations, always use
@conditional_tooldecorator - MANDATORY: Verify that ALLOW_MODIFY_OPERATIONS=false properly hides modify tools from registration
- NEVER use:
@mcp.tool()for operations that can modify/delete OpenStack resources - Always test: Tool visibility with both
ALLOW_MODIFY_OPERATIONS=trueandALLOW_MODIFY_OPERATIONS=false - Pattern: Read-only tools use
@mcp.tool(), modify tools use@conditional_tool
Architecture Overview
This is an MCP (Model Context Protocol) Server for OpenStack Operations - a Python service providing real-time OpenStack cluster management through 24+ tools. The architecture follows a layered pattern:
src/mcp_openstack_ops/functions.py(3000+ lines): Core OpenStack SDK operations with connection cachingsrc/mcp_openstack_ops/mcp_main.py(1400+ lines): FastMCP tool definitions and conditional safety systemsrc/mcp_openstack_ops/prompt_template.md: AI assistant behavior guide with tool patterns
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.
- 2d ago First seen ยท 154 lines ยท 1,488 tokens per session scan A 0d111176d38b
MCP-OpenStack-Ops copilot-instructions.md is an instructions file published in the GitHub repository call518/MCP-OpenStack-Ops (41 stars, last pushed 23d ago), licensed MIT. It adds 1,488 tokens to every session, about $0.0074 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
RivalSearchMCP AGENTS.md
Instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
RivalSearchMCP CLAUDE.md
Instructions for damionrashford/RivalSearchMCP, covering claude.md, project overview, development commands, setup & running and set up pre-commit hooks.
docs-mcp-server AGENTS.md
Instructions for pankaj28843/docs-mcp-server, covering docs-mcp-server, agent compatibility, build & test commands, always prefix python commands with uv run and core principles.
tailscale-mcp CLAUDE.md
Instructions for sandraschi/tailscale-mcp, covering tailscale-mcp โ claude code guide, standards and key files.
terragrunt-mcp-server copilot-instructions.md
Instructions for omattsson/terragrunt-mcp-server, covering terragrunt mcp server - ai assistant guide, architecture, key patterns, development and schema drift detection.
azure-compliance-mcp CLAUDE.md
Claude Code instructions for vivekanjana76/azure-compliance-mcp, covering claude.md โ azure-compliance-mcp, what this is, tech stack (pin these), architecture and github automation โ how you (claude) manage this repo.