agentmods.dev

runbook-bridge AGENTS.md

runbook-bridge AGENTS.md is an instructions file for Codex, OpenCode from coco-ari/runbook-bridge. It costs 1,454 tokens per session, scanned A, original, MIT.

Repository-specific instructions for the RunbookBridge desktop application. They describe its architecture, security rules, data model, and editing conventions.

In plain words
What is it for?
Use them when modifying RunbookBridge’s Electron app, MCP connection, workspace storage, renderer, or security controls.
Why use it?
They help coding agents change the right files while preserving security boundaries, compatibility names, and unrelated work.

Instructions file for CodexOpenCode

not rated 0 3d ago A scan 1,454 tokens original MIT
View the source file coco-ari/runbook-bridge
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/coco-ari/runbook-bridge/agents-md
Clone the repo
git clone --depth 1 https://github.com/coco-ari/runbook-bridge

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 runbook-bridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coco-ari/runbook-bridge/agents-md.svg)](https://agentmods.dev/instructions/coco-ari/runbook-bridge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/coco-ari/runbook-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/coco-ari/runbook-bridge/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,454 This file is loaded in full into every session.
When invoked 1,454 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 $0.01454 $0.01454
Opus 5 $0.00727 $0.00727
Sonnet 5 $0.00291 $0.00291
Haiku 4.5 $0.00145 $0.00145

Measured 2d ago against content hash 96ac89069368, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runbook-bridge 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 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.

AGENTS.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RunbookBridge agent guide

These instructions apply to the entire canonical repository. Keep changes focused and preserve unrelated working-tree edits.

Active architecture

  • src/main.mjs composes the Electron main process, local Broker, stores, plugin runtimes, connection managers, and V2 IPC.
  • src/mcp-v2.mjs is the shipped MCP entry point; src/v2-service.mjs is the shared application/service boundary; src/ipc-v2.mjs and src/preload.cjs expose the desktop API.
  • src/workspace-store.mjs owns the Project -> Environment -> Plugin persisted model. Credential material is handled by the credential vault/store modules, not workspace YAML.
  • src/broker-server.mjs and src/broker-client.mjs bridge MCP to the running desktop process. Server, MySQL, and Redis behavior belongs in their operation/runtime modules.
  • src/context-manager.mjs, src/operation-gate.mjs, src/confirmation-manager.mjs, src/command-policy.mjs, and src/mysql-policy.mjs enforce security boundaries.
  • renderer/v2/index.html and renderer/v2/src/ are the active React Renderer source. Vite generates renderer-build/v2/; Electron loads and packages that generated directory, which must never be hand-edited or committed. The legacy Renderer files, the files directly under renderer/, src/mcp.mjs, src/connection-manager.mjs, and src/plugin-draft-service.mjs have been removed. Keep the explicit source-Renderer and !src/mcp.mjs package exclusions plus the absence tests as tombstones; do not recreate these paths unless a task explicitly requires a compatibility restoration with matching tests.
  • Tests live in test/*.test.mjs; Electron smoke and package verification entry points live in scripts/.

Stable identities and compatibility names

  • Repository and package: runbook-bridge; installed desktop product: Agent运维工作台; current Electron app/window name: AI 运维工具.
  • CLI bin: ai-ops-mcp; documented Codex MCP alias: agent-ops; MCP protocol server name: agent-ops-workbench.
  • Compatibility identifiers: application data directory AIOpsTool and Broker pipe prefix ai-ops-tool-*.
  • These names identify different integration layers; do not normalize or rename them as incidental cleanup. Any requested rename needs an explicit compatibility/migration plan for existing installs, Codex registrations, data directories, and pipe coordination, plus install/upgrade and packaged-MCP regression coverage.

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 1,454 tokens per session scan A 96ac89069368

Subscribe to this mod's changes

runbook-bridge AGENTS.md is an instructions file published in the GitHub repository coco-ari/runbook-bridge (0 stars, last pushed 3d ago), licensed MIT. It adds 1,454 tokens to every session, about $0.0073 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.

ai-agentcodexelectronmcprunbook
Related

Other instructions, from other repositories

vscode tree-widgets.instructions.md

Use when asked to consume workbench tree widgets in VS Code.

microsoft/vscode · 1,456 tokens

vscode accessibility.instructions.md

Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.

microsoft/vscode · 611 tokens

vscode writing-tests.instructions.md

VS Code test writing guidelines — unit tests, integration tests, snapshot tests, and clean teardown patterns. Reference when writing or updating tests.

microsoft/vscode · 558 tokens

vscode interactive.instructions.md

Architecture documentation for VS Code interactive window component. Use when working in src/vs/workbench/contrib/interactive.

microsoft/vscode · 938 tokens

vscode notebook.instructions.md

Architecture documentation for VS Code notebook and interactive window components. Use when working in src/vs/workbench/contrib/notebook/.

microsoft/vscode · 1,105 tokens

vscode chat.instructions.md

Chat feature area coding guidelines.

microsoft/vscode · 370 tokens