workspace-ralph-orchestrator

workspace-ralph-orchestrator is a skill for Claude Code, Codex from T-0-co/t-0-spec-kit-ralph. It costs 70 tokens per session (3,772 once invoked), scanned A, original, MIT.

A skill for controlling Ralph automation loops, which repeatedly execute planned development tasks. It can start, stop, monitor, or inspect those loops in a workspace.

In plain words
What is it for?
Use it to start Ralph from a specification directory, choose parallel or sequential work, check status, view progress, or stop a run gracefully.
Why use it?
It gives developers a way to manage long-running automated task runs and stop them while preserving their progress.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; names the TodoWrite tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is WORKTREE_BASE="../worktrees".

Good fit Use it to start Ralph from a specification directory, choose parallel or sequential work, check status, view progress, or stop a run gracefully.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/T-0-co/t-0-spec-kit-ralph
agentmods
npx agentmods add skills/t-0-co/t-0-spec-kit-ralph/workspace-ralph-orchestrator

Made for: Claude Code, Codex.

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 workspace-ralph-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/t-0-co/t-0-spec-kit-ralph/workspace-ralph-orchestrator/github.svg)](https://agentmods.dev/skills/t-0-co/t-0-spec-kit-ralph/workspace-ralph-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/t-0-co/t-0-spec-kit-ralph/workspace-ralph-orchestrator"><img src="https://agentmods.dev/badge/skills/t-0-co/t-0-spec-kit-ralph/workspace-ralph-orchestrator/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 workspace-ralph-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/t-0-co/t-0-spec-kit-ralph/workspace-ralph-orchestrator"><img src="https://agentmods.dev/badge/skills/t-0-co/t-0-spec-kit-ralph/workspace-ralph-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,772 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 $0.00070 $0.03772
Opus 5 $0.00035 $0.01886
Sonnet 5 $0.00014 $0.00754
Haiku 4.5 $0.00007 $0.00377

Measured 12d ago against content hash 6678fb1a1110, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

workspace-ralph-orchestrator 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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (ralph-context.sh, scripts/ralph_ctl.sh, scripts/ralph_status.py), 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.

.agents/skills/workspace-ralph-orchestrator/SKILL.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Ralph Orchestrator

Orchestrate Ralph automation loops via tmux sessions with full control from Claude Code.

Quick Reference

Command Description
ralph start <spec_dir> Start Ralph loop (parallel batches enabled by default)
ralph --no-parallel <spec_dir> Run sequentially (disable parallel batches)
ralph stop Hard kill Ralph processes
ralph stop --graceful Graceful stop after current task
ralph status <spec_dir> Show current progress
ralph context <spec_dir> --simple --loop Live dashboard (recommended)
ralph --worktree <spec_dir> Run in isolated worktree

Stop Ralph after the current task completes, preserving state:

# Create stop file - Ralph checks this between tasks
touch <spec_dir>/.ralph/.stop

# Example:
touch specs/001-my-feature/.ralph/.stop

Ralph will:

  1. Finish the current task
  2. Update progress.json with final state
  3. Log the graceful stop
  4. Exit cleanly

From Claude Code, use this pattern:

# Graceful stop
SPEC_DIR="specs/001-my-feature"
touch "$SPEC_DIR/.ralph/.stop"
echo "Stop file created - Ralph will stop after current task"

Hard Stop (Immediate)

When you need to stop immediately:

# Kill specific session
tmux kill-session -t ralph-001 2>/dev/null

# Kill all Ralph processes
pkill -f "ralph.sh"
pkill -f "timeout.*claude"

# Kill Playwright tests (if running)
pkill -f "playwright"
pkill -f "npx.*playwright"

# Nuclear option - kills ALL tmux
tmux kill-server

Complete cleanup script:

# Stop everything Ralph-related
tmux kill-session -t ralph-001 2>/dev/null
pkill -f "ralph.sh"
pkill -f "timeout.*claude"
pkill -f "playwright"
pkill -f "npx.*playwright"

Important: After hard stop, manually update progress.json to document state.

Viewing Claude Session Context

Ralph spawns a Claude Code session for each task. Use the included helper script for a complete overview.

Read the full file on GitHub · 470 lines

Files

What ships with it

4 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. 12d ago First seen · 470 lines · 70 tokens per session scan A 6678fb1a1110

Subscribe to this mod's changes

workspace-ralph-orchestrator is a skill published in the GitHub repository T-0-co/t-0-spec-kit-ralph (10 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 3,772 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.