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.
npx agentmods add instructions/joshjancula/ralph/agents-mdgit clone --depth 1 https://github.com/JoshJancula/ralphWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.05179 | $0.05179 |
| Opus 5 | $0.02589 | $0.02589 |
| Sonnet 5 | $0.01036 | $0.01036 |
| Haiku 4.5 | $0.00518 | $0.00518 |
Grade B, and why
ralph AGENTS.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| **Claude** | `~/.claude/settings.json`, `.claude/settings.json`, `.claude/settings.local.json`, user/global rules, skills, hooks, plugins, permissions, memory | Agent `mcp_servers` merged over ambient, then Ralph's pro How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Audience: This file is the agent contract for Claude Code, Cursor, Codex, OpenCode, Antigravity, and other AI assistants working in this repository. Human operators should use README.md and docs/. Open a docs page only when this file points you there.
Overview
Ralph is a framework for organizing AI coding assistant workflows. It supports the Cursor, Claude, Codex, OpenCode, and Antigravity runtimes. It provides:
- Plan-first loop:
ralph create planis the main entry point.--format classicis the zero-dependency markdown checklist path;--format yamlis the YAML-frontmatter TODO queue path. For staged multi-agent work, useralph create orc. Older format tokens (standard,structured,pipeline,cursor) are still accepted as aliases foryaml. - Orchestration: Pipeline orchestration routes TODOs and stages by runtime, agent, and model across the supported runtimes (Cursor, Claude, Codex, OpenCode, Antigravity). It shares context through
produces/requiresartifact declarations and explicit artifact paths in TODO content so required inputs surface automatically in each stage's prompt. - Agents: Prebuilt agent profiles for specialized work (research, architect, implementation, code-review, qa, security)
- Dashboard: Optional Node UI for monitoring plan execution and artifact generation
Ralph is installed into projects via ./install.sh. See Reference map → docs/INSTALL.md.
Runtime roots (this repo):
.cursor,.claude,.codex,.opencode, and.agentsat the repo root are project-owned directories for Ralph's own development workflow.bundle/.cursor/,bundle/.claude/,bundle/.codex/,bundle/.opencode/, andbundle/.agents/are installable framework defaults and templates for downstream projects; editing bundle paths does not change repo-root runtime config..ralph/at the repo root is a symlink tobundle/.ralph/(shared scripts); edits underbundle/.ralph/are reflected there.
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.
- 3d ago First seen · 277 lines · 5,179 tokens per session scan B b5ce168ca5c8
ralph AGENTS.md is an instructions file published in the GitHub repository JoshJancula/ralph (10 stars, last pushed 17d ago), licensed MIT. It adds 5,179 tokens to every session, about $0.0259 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.