ralph-gold AGENTS.md

ralph-gold AGENTS.md is an instructions file for Codex, OpenCode from jscraik/ralph-gold. It costs 1,581 tokens per session, scanned A, original, MIT.

A repository instruction file for ralph-gold, a Python command-line tool that coordinates repeated work between AI agents and saves its state on disk. It sets rules for project exploration, tooling, documentation, and execution.

In plain words
What is it for?
Use it when changing the ralph-gold CLI, its agent work loops, durable state, tests, or project documentation.
Why use it?
It keeps contributions consistent with the repository’s package manager, workflow requirements, and development conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/jamiecraik/.codex/instructions/tooling.md.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 ralph-gold AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jscraik/ralph-gold/agents-md.svg)](https://agentmods.dev/instructions/jscraik/ralph-gold/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jscraik/ralph-gold/agents-md"><img src="https://agentmods.dev/badge/instructions/jscraik/ralph-gold/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,581 This file is loaded in full into every session.
When invoked 1,581 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 5.1 $0.01581 $0.01581
Opus 5 $0.00790 $0.00790
Sonnet 5 $0.00316 $0.00316
Haiku 4.5 $0.00158 $0.00158

Measured 5d ago against content hash 93df3e163c0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ralph-gold 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 5d 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

schema_version: 1

Repository Guidelines

ralph-gold is a uv-first Python CLI orchestrator for deterministic multi-agent work loops with durable filesystem state.

Mandatory workflow snippet

  1. Explore project first, then invoke skill.
  2. IMPORTANT: Prefer retrieval-led reasoning over pre-training-led reasoning for any React, Tauri, Apps-SDK-ui, Tailwind, Vite, Storybook + Chat Widget tasks.
  3. Add a Table of Contents for docs.

Required essentials

  • Package manager: uv.
  • Non-standard build/typecheck commands: none.
  • Default compatibility posture: canonical-only.

Tooling essentials

  • Run shell commands with zsh -lc.
  • Prefer rg, fd, and jq for search, file discovery, and JSON.
  • Before choosing tools, read /Users/jamiecraik/.codex/instructions/tooling.md.
  • Ask before adding dependencies or system settings.
  • Execution mode: single-threaded by default; do not parallelize or spawn subagents unless explicitly requested.

References (informational)

  • Global protocol index: /Users/jamiecraik/.codex/AGENTS.md
  • Security baseline: /Users/jamiecraik/.codex/instructions/standards.md
  • RVCP source of truth: /Users/jamiecraik/.codex/instructions/rvcp-common.md

Global discovery order

  1. /Users/jamiecraik/.codex/AGENTS.md
  2. Nearest repo AGENTS.md
  3. Linked instruction files
  4. If conflicts appear, pause and ask which instruction wins

Documentation map

Table of Contents

Local Memory usage

  • Follow /Users/jamiecraik/.codex/instructions/local-memory.md.
  • Mandatory workflow before durable notes:
    • bootstrap(mode="minimal", include_questions=true, session_id="repo:<name>:task:<id>")
    • search(query="...", session_id="repo:<name>:task:<id>")
  • Store durable facts only; never store secrets, tokens, keys, or PII.

Read the full file on GitHub · 151 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. 5d ago First seen · 151 lines · 1,581 tokens per session scan A 93df3e163c0f

Subscribe to this mod's changes

ralph-gold AGENTS.md is an instructions file published in the GitHub repository jscraik/ralph-gold (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,581 tokens to every session, about $0.0079 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.