ralph-loop

An automated coding loop that reads a PRD, or product requirements document, and handles its user stories one at a time. Each iteration starts a fresh AI coding session to implement, test, and commit a story.

In plain words
What is it for?
It helps execute PRD user stories with Copilot, Claude, or AMP, with optional limits and separate ports for parallel runs.
Why use it?
It turns a list of planned features into repeated implementation and testing cycles without manually starting each session.

Skill for Claude CodeCodex

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 skills/patelr3/agents/ralph-loop
Any agent
npx skills add patelr3/agents --skill ralph-loop
Clone the repo
git clone --depth 1 https://github.com/patelr3/agents

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 945 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 $0.00057 $0.00945
Opus 5 $0.00028 $0.00473
Sonnet 5 $0.00011 $0.00189
Haiku 4.5 $0.00006 $0.00094

Measured 2d ago against content hash aa3fc11103e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph-loop 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ralph.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/rav-town/skills/ralph-loop/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph Loop

Runs the Ralph execution loop (ralph.sh) that iterates through PRD user stories, spawning a fresh AI coding session per iteration.


The Job

Execute the ralph.sh script from this skill's scripts/ directory. The script reads a PRD JSON file and iterates through its user stories, invoking an AI tool (Copilot, Claude, or AMP) once per story.


Usage

${CLAUDE_PLUGIN_ROOT}/skills/ralph-loop/scripts/ralph.sh --prd <path-to-prd.json> [--tool copilot|claude|amp] [--port-offset N] [max_iterations]

Parameters

Parameter Required Default Description
--prd <file> Yes Path to the PRD JSON file (e.g., docs/prds/prd-2026-03-15-task-status.json)
--tool <name> No copilot AI backend: copilot, claude, or amp
--port-offset N No Port offset for parallel isolation (API=3001+N, Web=3000+N)
max_iterations No 10 Maximum loop iterations before aborting

Example

# Run with Copilot (default), 12 iterations max
${CLAUDE_PLUGIN_ROOT}/skills/ralph-loop/scripts/ralph.sh \
  --prd docs/prds/prd-2026-03-15-task-status.json \
  --port-offset 10 \
  12

What the Loop Does

Each iteration spawns a fresh AI session that:

  1. Reads the PRD JSON file
  2. Reads the progress log for context from prior iterations
  3. Picks the highest-priority story where passes: false
  4. Implements that one story
  5. Runs quality checks (typecheck, lint, tests)
  6. Commits with message: feat: [US-XXX] - Story Title
  7. Marks the story as passes: true in the PRD JSON
  8. Appends learnings to the progress file
  9. Checks if all stories pass — if so, updates PRD status to complete, creates PR, enables auto-merge, and outputs <promise>PRD-COMPLETE</promise>

File Expectations

The script expects:

  • PRD JSON: The file passed via --prd (e.g., docs/prds/prd-2026-03-15-task-status.json)
  • Progress file: Derived from the PRD filename — prd- prefix replaced with progress-, .json replaced with .txt (e.g., docs/prds/progress-2026-03-15-task-status.txt)
  • CLAUDE.md prompt: Located at ${CLAUDE_PLUGIN_ROOT}/skills/ralph-loop/scripts/CLAUDE.md (same directory as ralph.sh)

Read the full file on GitHub · 102 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 102 lines · 57 tokens per session scan A aa3fc11103e6

Subscribe to this mod's changes

ralph-loop is a skill published in the GitHub repository patelr3/agents (2 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 945 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens