runwhen-platform-mcp AGENTS.md

runwhen-platform-mcp AGENTS.md is an instructions file for Codex, OpenCode from runwhen-contrib/runwhen-platform-mcp. It costs 2,550 tokens per session, scanned A, original, Apache-2.0.

An instruction document for agents working on a RunWhen platform server. RunWhen is a system for investigating infrastructure and running automated checks, and an MCP server connects coding agents to its tools.

In plain words
What is it for?
Use it when configuring authentication, choosing between workspace chat and direct tools, or working with the three RunWhen agent roles.
Why use it?
It prevents common setup and routing mistakes, such as leaving out the required workspace name or using the wrong kind of platform tool.

Instructions file for CodexOpenCode

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

Made for: Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/runwhen-contrib/runwhen-platform-mcp/agents-md.svg)](https://agentmods.dev/instructions/runwhen-contrib/runwhen-platform-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/runwhen-contrib/runwhen-platform-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/runwhen-contrib/runwhen-platform-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,550 This file is loaded in full into every session.
When invoked 2,550 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 $0.02550 $0.02550
Opus 5 $0.01275 $0.01275
Sonnet 5 $0.00510 $0.00510
Haiku 4.5 $0.00255 $0.00255

Measured 3d ago against content hash 2c599b97e38c, 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 AGENTS.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.

AGENTS.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — RunWhen Platform MCP Server

This repository provides an MCP server and Cursor plugin for the RunWhen AI SRE platform. Three agent personas interact with the platform through MCP tools:

  • runwhen-sre — Investigates and troubleshoots infrastructure by querying the platform for issues, run sessions, and production insights.
  • runwhen-task-builder — Builds workspace-specific health checks and automation tasks by analyzing code and infrastructure, then testing and committing SLXs.
  • runwhen-codecollection-author — Builds reusable, parameterized codebundles that work across any environment. Tests them as SLXs in a workspace and cleans up after validation.

Authentication

  • Local (stdio) — The MCP client passes RUNWHEN_TOKEN (and RW_API_URL) in environment variables; there is no OAuth handshake in-process.
  • Remote (HTTP) — Each request carries auth: usually Authorization: Bearer with a JWT or Personal Access Token. When the server is deployed with MCP_BASE_URL and MCP_PAPI_OAUTH_CLIENT_ID / MCP_PAPI_OAUTH_CLIENT_SECRET, MCP clients that support remote OAuth can sign in via the browser; discovery is at {MCP_BASE_URL}/.well-known/oauth-authorization-server, and the upstream OAuth app must allow redirect {MCP_BASE_URL}/auth/callback. Configure these variables on the server (not in the agent’s MCP client env). See the repo README section OAuth for remote HTTP deployments.

Important: workspace_name is required

Most tools require a workspace_name parameter. Always provide it explicitly — do not omit it or rely on defaults. If you don't know the workspace name, call list_workspaces first to discover available workspaces.

Tool Routing — workspace_chat vs direct tools

workspace_chat is the primary investigation tool. The agent searches (keyword, semantic, and fuzzy), navigates and correlates across resources, SLXs, issues, run sessions, and the knowledge base, and returns rich reports, diagrams, and tables. It produces materially better answers than combining multiple direct API calls for investigative questions.

Read the full file on GitHub · 171 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 · 171 lines · 2,550 tokens per session scan A 2c599b97e38c

Subscribe to this mod's changes

runwhen-platform-mcp AGENTS.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 2,550 tokens to every session, about $0.0128 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

siclaw AGENTS.md

Instructions for scitix/siclaw, covering siclaw project instructions, project shape, before risky edits, verification and stable boundaries.

scitix/siclaw · 829 tokens

aks-mcp copilot-instructions.md

Instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.

Azure/aks-mcp · 889 tokens

tunnel-manager AGENTS.md

AGENTS.md instructions for Knuckles-Team/tunnel-manager, covering agents.md, tech stack & architecture, architecture diagram, workflow diagram and commands (run these exactly).

Knuckles-Team/tunnel-manager · 4,710 tokens

obsidian-multivault-mcp AGENTS.md

Instructions for bepitulaz/obsidian-multivault-mcp, covering agents.md — deploying this mcp server on the vps, vps facts (example — change to match yours), gather before you start, do (high level — exact commands in deploy.md) and definition of done (verify — do not assume).

bepitulaz/obsidian-multivault-mcp · 1,376 tokens

remote-mcp-functions-python copilot-instructions.md

Instructions for Azure-Samples/remote-mcp-functions-python: You are an ai assistant tasked assisting the developer to build and deploy MCP Servers successfully using Azure Functions. Our ultimate goal is for the user to be able to complete this quickstart guide, where the app is deployed and healthy in azure, and the…

Azure-Samples/remote-mcp-functions-python · 314 tokens

obsidian-multivault-mcp CLAUDE.md

Instructions for bepitulaz/obsidian-multivault-mcp: See AGENTS.md for the deployment brief, and DEPLOY.md for the full step-by-step VPS runbook.

bepitulaz/obsidian-multivault-mcp · 36 tokens