runwhen-platform-mcp copilot-instructions.md

runwhen-platform-mcp copilot-instructions.md is an instructions file for GitHub Copilot from runwhen-contrib/runwhen-platform-mcp. It costs 562 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a RunWhen MCP server, which connects an AI assistant to infrastructure investigations and automation. A workspace name identifies the infrastructure workspace being used.

In plain words
What is it for?
Use them to investigate infrastructure, create or run automation tasks, manage workspaces and configure the RunWhen platform.
Why use it?
They explain which tools to use for searching infrastructure data and which direct tools handle tasks, scripts and configuration.

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/runwhen-contrib/runwhen-platform-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/runwhen-contrib/runwhen-platform-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 runwhen-platform-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/runwhen-contrib/runwhen-platform-mcp/copilot-instructions.svg)](https://agentmods.dev/instructions/runwhen-contrib/runwhen-platform-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/runwhen-contrib/runwhen-platform-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/runwhen-contrib/runwhen-platform-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 562 This file is loaded in full into every session.
When invoked 562 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 $0.00562 $0.00562
Opus 5 $0.00281 $0.00281
Sonnet 5 $0.00112 $0.00112
Haiku 4.5 $0.00056 $0.00056

Measured 3d ago against content hash c94776bf1503, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runwhen-platform-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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RunWhen Platform MCP Server — Copilot Instructions

This repository provides an MCP server for the RunWhen AI SRE platform. Use the MCP tools to investigate infrastructure, build automation tasks, and manage workspace configuration.

workspace_name is required

Most tools require a workspace_name parameter. Always provide it. If unknown, call list_workspaces first.

Tool Routing

workspace_chat is the primary investigation tool — prefer it for any question that involves searching, correlating, or interpreting infrastructure data. It has internal semantic search, keyword grep, and resource graph traversal that produce better answers than combining direct API calls.

Use direct tools only for: executing tasks (run_slx), task authoring (validate_script, run_script_and_wait, commit_slx), registry operations, chat config CRUD, KB mutations, and runner configuration.

Available Skills

This project includes detailed workflow skills in skills/ (also at .github/skills/). Use these for multi-step tasks — they contain step-by-step instructions, templates, and examples.

Skill When to use
build-runwhen-task Building a new health check or automation task
find-and-deploy-codebundle Deploying a pre-built codebundle from the registry
run-existing-slx Running an existing SLX in a workspace
verify-mcp-setup Validating the MCP server is installed and working
create-ai-assistant Creating a new AI assistant (agent/persona) and tailoring it with rules and commands
manage-rules Creating or updating workspace chat rules
manage-commands Creating or updating workspace chat commands
manage-knowledge Creating or updating knowledge base articles
discover-secrets Finding available workspace secrets
discover-locations Finding available runner locations
configure-resource-path Setting resource paths for SLX indexing
configure-hierarchy Organizing SLXs with hierarchy tags
build-operational-context Building a RUNWHEN.md file for a project

Read the full file on GitHub · 51 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 · 51 lines · 562 tokens per session scan A c94776bf1503

Subscribe to this mod's changes

runwhen-platform-mcp copilot-instructions.md is an instructions file published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 19d ago), licensed Apache-2.0. It adds 562 tokens to every session, about $0.0028 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.