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/brenbuilds1/copilot-ralph/agents-mdgit clone --depth 1 https://github.com/brenbuilds1/copilot-ralphWrote 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.
[](https://agentmods.dev/instructions/brenbuilds1/copilot-ralph/agents-md)<a href="https://agentmods.dev/instructions/brenbuilds1/copilot-ralph/agents-md"><img src="https://agentmods.dev/badge/instructions/brenbuilds1/copilot-ralph/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00589 | $0.00589 |
| Opus 5 | $0.00295 | $0.00295 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
copilot-ralph 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository contains Ralph for GitHub Copilot CLI - an autonomous AI agent loop.
Project Structure
.
├── ralph.sh # Main loop script
├── prompt.md # Instructions for each Copilot iteration
├── prd.json.example # Example PRD format
├── skills/ # Agent skills
│ └── prd/ # PRD generator skill
│ └── SKILL.md # PRD generation instructions
├── README.md # User documentation
└── AGENTS.md # This file
Skills
prd-generator (skills/prd/SKILL.md)
Generates prd.json files for Ralph autonomous implementation.
Triggers: "create a PRD", "generate a PRD", "plan a feature", "write user stories", "set up Ralph for [feature]"
Workflow:
- Asks 3-5 clarifying questions with A/B/C/D options
- Generates structured prd.json with properly-sized user stories
- Each story includes specific, verifiable acceptance criteria
Commands
# Run Ralph with default 10 iterations
./ralph.sh
# Run with custom max iterations
./ralph.sh 25
# Check story status
cat prd.json | jq '.userStories[] | {id, title, passes}'
# View progress log
cat progress.txt
How It Works
ralph.shruns a bash loop- Each iteration calls:
copilot -p "$PROMPT" --allow-all-tools - Copilot reads
prd.jsonandprogress.txtfor context - Copilot implements one story, commits, updates
prd.json - Loop checks for
<promise>COMPLETE</promise>to exit - Otherwise, next iteration picks up remaining work
Key Files Created During Runs
| File | Purpose |
|---|---|
prd.json |
User's PRD with stories (copy from prd.json.example) |
progress.txt |
Append-only log of learnings |
.ralph-last-branch |
Tracks branch for archiving |
archive/ |
Previous runs archived here |
Modifying This Project
- prompt.md: Edit to customize agent behavior, add project-specific commands
- ralph.sh: Modify loop logic, add pre/post hooks
- prd.json.example: Update template for your use cases
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.
- 5d ago First seen · 78 lines · 589 tokens per session scan A c8b75be92a70
copilot-ralph AGENTS.md is an instructions file published in the GitHub repository brenbuilds1/copilot-ralph (50 stars, last pushed 7mo ago), licensed MIT. It adds 589 tokens to every session, about $0.0029 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.
Other instructions, from other repositories
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.
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.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.