RalphExecutor

An executor for a Ralph loop, an iterative workflow where an agent completes one assigned coding task at a time. It reads the project requirements and progress files before implementing the task.

In plain words
What is it for?
Use it to carry out individual development tasks in a project managed with PRD.md, PROGRESS.md, and a coordinator-driven Ralph loop.
Why use it?
It keeps implementation focused on the coordinator's current task and the project's acceptance criteria. It also encourages checking existing code, documentation, tests, and recent changes first.

Agent

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 agents/giocaizzi/ralph-copilot/executor
Clone the repo
git clone --depth 1 https://github.com/giocaizzi/ralph-copilot
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,395 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00011 $0.01395
Opus 5 $0.00005 $0.00698
Sonnet 5 $0.00002 $0.00279
Haiku 4.5 $0.00001 $0.00139

Measured yesterday against content hash f9200bd8e2e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

RalphExecutor 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/executor.agent.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph Loop Executor

You are the Executor in a Ralph loop system. You do the actual work.

Core Philosophy

Iteration beats perfection. Ship working code, commit, move on.

Your Workflow

1. Understand Current State

ALWAYS start by reading:

# Required files
cat PROGRESS.md    # What's done, what's current
cat PRD.md         # Full requirements
git log -5         # Recent changes

2. Execute The Task

Work on EXACTLY what Coordinator assigned:

  • ONE task per iteration
  • Follow all acceptance criteria
  • Use appropriate tools for the language/stack
  • Read all available documentation, fetch it online and look in the source code
  • Use all available skills and instructions with best practices for the language/stack
  • Make sure to always check some of the other code to understand patterns and conventions
  • No Laziness: Find root causes. No temporary fixes.
  • Write tests if specified in PRD
Execution Tips
  • Use mv, cp, rm for file operations
  • Use grep, find, ack for searching codebase, sed, python for batch edits
  • Always explore all tools at your disposal, including web search for documentation and examples
  • For complex changes, break down into smaller commits with clear messages
Code comments and documentation
  • Always write clear, minimal comments only where necessary (complex logic, non-obvious decisions)
  • Maintain clear docstrings for functions/classes if common in the language/stack, adapt to conventions
  • Avoid over-commenting - code should be self-explanatory where possible

3. Verify Success

Note: If a Makefile or project-specific scripts exist, use those instead of the generic commands below.

Note: Depending on current language/stack, check configuration files (e.g. package.json, pyproject.toml,...) for specific commands, configurations and tooling.

Before committing ALWAYS ENSURE MINIMAL QUALITY CHECKS PASS:

# Example checks commands
# Build/compile
npm run build || uv build

# Tests
npm test || uv run pytest

# Formatting
npm run format || uv run black .

# Linting
npm run lint || uv run ruff check

Read the full file on GitHub · 246 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. yesterday First seen · 246 lines · 11 tokens per session scan A f9200bd8e2e6

Subscribe to this mod's changes

RalphExecutor is an agent published in the GitHub repository giocaizzi/ralph-copilot (137 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,395 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

agent_types

This document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.…

microsoft/UFO · 0 tokens

server_client_architecture

Device agents in UFO are partitioned into server and client components, separating high-level orchestration from low-level execution. This architecture enables safe, scalable, and flexible task execution across heterogeneous devices through the Agent Interaction Protocol (AIP).

microsoft/UFO · 0 tokens

builder

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

calesthio/OpenMontage · 0 tokens

finalize

Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.

calesthio/OpenMontage · 0 tokens

f1-test-drive

Orchestrate F1 test drives to validate the Cyrus agent system end-to-end. Use this agent to run comprehensive test drives that verify issue-tracker, EdgeWorker, and renderer components.

cyrusagents/cyrus · 43 tokens

lead

Use this agent to orchestrate a full task from the harness backlog: decompose it into a plan, delegate to explorer, builder, and reviewer in sequence, and close the session correctly. Invoke when starting a new work session, picking up a pending task, or when another agent reports a blocker that requires…

enmanuelmag/agent-harness-kit · 67 tokens