ralph

ralph is a command for Claude Code from T-0-co/t-0-spec-kit-ralph. It costs 14 tokens per session (597 once invoked), scanned A, original, MIT.

A command that runs the tasks listed in a project's tasks.md file, giving each task a fresh Claude session and checking the build or tests between tasks.

In plain words
What is it for?
Use it to carry out a written feature specification step by step, with optional dry runs and resume support.
Why use it?
It reduces the need to start and track each task manually. It can also preview work or continue after a fix.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to carry out a written feature specification step by step, with optional dry runs and resume support.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/t-0-co/t-0-spec-kit-ralph/ralph
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.

Clone the repo
git clone --depth 1 https://github.com/T-0-co/t-0-spec-kit-ralph

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/t-0-co/t-0-spec-kit-ralph/ralph/github.svg)](https://agentmods.dev/commands/t-0-co/t-0-spec-kit-ralph/ralph)
Your own site
<a href="https://agentmods.dev/commands/t-0-co/t-0-spec-kit-ralph/ralph"><img src="https://agentmods.dev/badge/commands/t-0-co/t-0-spec-kit-ralph/ralph/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ralph

Your own site · 80×15
<a href="https://agentmods.dev/commands/t-0-co/t-0-spec-kit-ralph/ralph"><img src="https://agentmods.dev/badge/commands/t-0-co/t-0-spec-kit-ralph/ralph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00014 $0.00597
Opus 5 $0.00007 $0.00298
Sonnet 5 $0.00003 $0.00119
Haiku 4.5 $0.00001 $0.00060

Measured 10d ago against content hash 93437b938273, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ralph 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 10d 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/commands/ralph.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ralph - Autonomous Task Execution

User Input

$ARGUMENTS

Overview

Ralph Wiggum Loop executes tasks from tasks.md with fresh Claude context per task and build/test verification between iterations.

Usage

The user can invoke this command with optional arguments:

/ralph                    # Run on auto-detected spec
/ralph specs/001-feature/ # Run on specific spec
/ralph --dry-run          # Preview only
/ralph --resume           # Resume after fix

Execution

  1. Locate spec directory

    • If path provided in $ARGUMENTS, use that
    • Otherwise, look for tasks.md in current directory or specs/*/tasks.md
  2. Validate prerequisites

    • Ensure tasks.md exists
    • Check for Claude CLI availability
    • Verify git repository (for commits)
  3. Execute Ralph

    # Prefer project-local wrapper, then installed binary, then .specify path
    RALPH_BIN="./ralph"
    if [[ ! -x "$RALPH_BIN" ]] && command -v ralph &> /dev/null; then
        RALPH_BIN="ralph"
    elif [[ ! -x "$RALPH_BIN" ]] && [[ -x "./.specify/ralph/bin/ralph" ]]; then
        RALPH_BIN="./.specify/ralph/bin/ralph"
    fi
    
    # All command arguments are passed through to ralph.sh unchanged
    # Example: /ralph --resume --worktree specs/001-feature/
    
    # Run with arguments
    $RALPH_BIN $ARGUMENTS
    
  4. Monitor progress

    • Watch .ralph/session.log for real-time progress
    • Check .ralph/progress.json for state

Options

Option Description
--dry-run Preview tasks without executing
--resume Resume from last state after fix
--phase N Start from specific phase
--budget N Stop if cost exceeds $N
--ui Enable terminal UI
--slack Enable Slack notifications

Notes

  • Ralph runs EXTERNAL to Claude sessions to get fresh context per task
  • Each task gets minimal, focused context from spec files
  • Build/test verification happens after each task
  • Auto-commits on success, blocks on failure
  • Resume capability for fixing blockers

Read the full file on GitHub · 83 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. 10d ago First seen · 83 lines · 14 tokens per session scan A 93437b938273

Subscribe to this mod's changes

ralph is a command published in the GitHub repository T-0-co/t-0-spec-kit-ralph (10 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 597 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 2026-08-31.