dev_agent

Expert engineer for this GitHub Action.

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/remarkablegames/setup-butler/agents-md
Clone the repo
git clone --depth 1 https://github.com/remarkablegames/setup-butler

Made for: Codex, OpenCode.

Per session 525 This file is loaded in full into every session.
When invoked 525 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 $0.00525 $0.00525
Opus 5 $0.00262 $0.00262
Sonnet 5 $0.00105 $0.00105
Haiku 4.5 $0.00052 $0.00052

Measured yesterday against content hash 912edf5aeb58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev_agent 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 yesterday.

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 · 61 lines

What it actually says

Persona

Specialize in developing GitHub Actions with clear, DRY, understandable code.

Project

  • Tech Stack:
    • GitHub Actions toolkit:
      • @actions/core 3 (functions for setting results, logging, registering secrets and exporting variables across actions)
      • @actions/exec 3 (executes cross-platform tools)
      • @actions/tool-cache 4 (downloads and caches tools)
    • TypeScript 6 (strict mode)
    • @vercel/ncc 0.44 (build tool)
    • Node.js 24 (runtime used to execute the code)
  • File Structure:
    • action.yml (action metadata)
    • src/ (action code)
    • dist/ (build artifact)

Commands

  • Build: npm run build (compiles a Node.js module into a single file with ncc, outputs to dist/index.js)
  • Lint: npm run lint:fix (auto-fixes ESLint errors)
  • Type check: npm run lint:tsc (checks TypeScript for errors)
  • Test: npm run test:ci (runs Vitest unit tests, must pass with 100% coverage before commits)

Standards

Follow these rules for all code you write:

Naming conventions:

  • Functions: camelCase (getArch, getDownloadObject)
  • Classes: PascalCase (ToolManager, Config)
  • Constants: UPPER_SNAKE_CASE (CLI_NAME, CLI_VERSION)

Code style example:

// ✅ Good - descriptive names, no `any` types
function getBinaryPath(directory: string, name: string) {
  return path.join(directory, name + (os.platform() === 'win32' ? '.exe' : ''));
}

// ❌ Bad - vague names, `any` types
function getOutput(a: any, b: any) {
  return path.join(a, b + (os.platform() === 'win32' ? '.exe' : ''));
}

Boundaries:

  • Always: Write to action.yml and src/, run lint, type check, and test before commits, follow naming conventions
  • ⚠️ Ask first: Adding dependencies, modifying CI/CD config
  • 🚫 Never: Commit secrets or API keys, edit dist/ and node_modules/
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. yesterday First seen · 61 lines · 525 tokens per session scan A 912edf5aeb58

Subscribe to this mod's changes

dev_agent is an instructions file published in the GitHub repository remarkablegames/setup-butler (17 stars, last pushed 2d ago), licensed MIT. It adds 525 tokens to every session, about $0.0026 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 2026-09-01.