agentmods.dev

coding-agent-runner AGENTS.md

Repository instructions for coding-agent-runner, a Node.js package that lets applications run local coding-agent command-line tools such as Codex, Claude Code, Cursor, OpenCode, and Pi.

In plain words
What is it for?
Use them when developing or changing the runner, its provider integrations, tests, and APIs such as detecting agents or streaming their output.
Why use it?
They clarify the package’s boundaries and public interfaces, helping contributors avoid adding unrelated application code, provider login, billing, or credential handling.

Instructions file for CodexOpenCode

23 1mo ago A scan 864 tokens original MIT
View the source file yinguangyao/coding-agent-runner
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/yinguangyao/coding-agent-runner/agents-md
Clone the repo
git clone --depth 1 https://github.com/yinguangyao/coding-agent-runner

Made for: Codex, OpenCode.

Per session 864 This file is loaded in full into every session.
When invoked 864 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 $0.00864 $0.00864
Opus 5 $0.00432 $0.00432
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00086 $0.00086

Measured 2d ago against content hash c9f271b22ad1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-agent-runner 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - coding-agent-runner

Project

coding-agent-runner is a Node.js package for running local coding-agent CLIs from application code.

Supported providers:

  • codex / codex-cli: Codex app-server over stdio JSON-RPC.
  • claude / claude-code-cli: Claude Code native stream-json.
  • cursor / cursor-cli: Cursor Agent over ACP.
  • opencode / opencode-cli: OpenCode over ACP.
  • pi / pi-cli: Pi ACP.

Boundaries

  • Do not import AI Workbench code, Electron code, server code, database code, or app-specific task queues.
  • Keep this package Node-only and publishable as a standalone npm package.
  • Do not add provider installation, login, credential storage, billing, UI, or sandbox policy.
  • Do not require real provider credentials in tests or CI.
  • Keep provider protocol code behind small public APIs and package-owned types.

Public API

Friendly APIs use short provider ids:

  • detectCliAgents()
  • createCodingAgentRunner()
  • streamCliAgent()
  • runCliAgent()

Top-level runner options include model, systemPrompt, mcpServers, and skills. Keep provider-specific mappings covered by tests when changing them:

  • Codex maps mcpServers to app-server config.mcp_servers and sends skills as structured skill input blocks plus developerInstructions skill references.
  • Claude maps mcpServers to --mcp-config; skill references are appended to the system prompt.
  • ACP providers pass mcpServers through session setup; skill references are wrapped into the fallback system prompt.

Lower-level APIs remain exported for advanced callers:

  • runAgentTurn()
  • runCodexTurn() / acquireCodexAppServer()
  • runClaudeNative()
  • AcpConnection
  • mapStreamEventToAgentEvents()
  • buildDefaultSpawn() / listProviderConfigs()

Development

Use npm, not yarn or pnpm, in this repository.

Run local verification before claiming completion:

npm run typecheck
npm test
npm run build
npm pack --dry-run

npm run check runs typecheck, tests, and build. It does not run npm pack --dry-run, so run pack separately before release-related changes.

Read the full file on GitHub · 94 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 · 94 lines · 864 tokens per session scan A c9f271b22ad1

Subscribe to this mod's changes

coding-agent-runner AGENTS.md is an instructions file published in the GitHub repository yinguangyao/coding-agent-runner (23 stars, last pushed 1mo ago), licensed MIT. It adds 864 tokens to every session, about $0.0043 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.

Backend and APIsTestingacpagent-client-protocolai-agentsclaude-codecli-wrappercodex
Related

Other instructions, from other repositories

intelligent-terminal agent-skills.instructions.md

Guidelines for creating high-quality Agent Skills for GitHub Copilot.

microsoft/intelligent-terminal · 3,888 tokens

intelligent-terminal rust-localization.instructions.md

Instructions for microsoft/intelligent-terminal, covering localization instructions for rust wta (yaml locale files), file structure, file format, the en-us.yml source file and non-translatable token rules.

microsoft/intelligent-terminal · 3,172 tokens

intelligent-terminal localization.instructions.md

Instructions for microsoft/intelligent-terminal, covering localization instructions for .resw resource files, components with localized resources, locale categories, authoritative locale list (from terminalapp) and adding or updating localized strings.

microsoft/intelligent-terminal · 2,935 tokens

intelligent-terminal copilot-instructions.md

Copilot instructions for microsoft/intelligent-terminal, covering copilot instructions for windows terminal, build, running, test and code formatting.

microsoft/intelligent-terminal · 1,953 tokens

intelligent-terminal instructions.instructions.md

Guidelines for creating high-quality custom instruction files for GitHub Copilot.

microsoft/intelligent-terminal · 1,777 tokens

intelligent-terminal AGENTS.md

AGENTS.md instructions for microsoft/intelligent-terminal, covering intelligent terminal, architecture, supported agents and settings, user-facing behavior and key files.

microsoft/intelligent-terminal · 1,777 tokens