ralph

ralph is a skill for Claude Code, Codex from jpicklyk/task-orchestrator. It costs 99 tokens per session (4,995 once invoked), scanned A, original, MIT.

A launcher for a Ralph-style script that repeatedly takes work from a queue and starts a fresh Claude coding process in an isolated Git worktree for each item.

In plain words
What is it for?
Draining a backlog, selecting work by a filter, setting processing bounds, and producing the command for an autonomous queue run.
Why use it?
It lets queued work be processed with separate contexts and isolated changes, while the launcher applies filters and limits before the script runs.

Skill for Claude CodeCodex

Part of the task-orchestrator plugin — 15 skills shipped together

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/jpicklyk/task-orchestrator/ralph
Any agent
npx skills add jpicklyk/task-orchestrator --skill ralph
Clone the repo
git clone --depth 1 https://github.com/jpicklyk/task-orchestrator

Made for: Claude Code, Codex.

Or install task-orchestrator, the plugin that ships this one along with the rest of its 15 skills.

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/skills/jpicklyk/task-orchestrator/ralph.svg)](https://agentmods.dev/skills/jpicklyk/task-orchestrator/ralph)
Your own site
<a href="https://agentmods.dev/skills/jpicklyk/task-orchestrator/ralph"><img src="https://agentmods.dev/badge/skills/jpicklyk/task-orchestrator/ralph.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00099 $0.04995
Opus 5 $0.00049 $0.02498
Sonnet 5 $0.00020 $0.00999
Haiku 4.5 $0.00010 $0.00500

Measured 4d ago against content hash 1273b937b612, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph scanned grade A with 1 finding 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 4d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

**Why a Node script, not bash.** Cross-platform — every Claude Code install has Node. Stdlib-only — no `npm install`, no plugin dependencies. The script uses `node:util.parseArgs`, `node:child_process.spawn`, and `node:f
claude-plugins/task-orchestrator/skills/ralph/SKILL.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ralph — Queue Drain Launcher

This skill is a launcher for the Ralph drain script (scripts/ralph-loop.mjs in this plugin). It does not run a loop in the current session. It helps you configure the right invocation, previews what will be processed, and emits the exact command to run.

The actual loop runs as a separate Node process. Each iteration spawns a fresh claude -p in its own git worktree (via Claude Code's -w flag), claims one item from the TO queue, and works it to terminal per the item's schema. Outcome is signaled via a RALPH_OUTCOME: JSON marker that the script parses for circuit-breaker decisions.

Why a separate script, not a slash-command loop? Per Geoff Huntley's canonical Ralph: the value comes from carving off small bits of work into independent context windows. Each iteration is a fresh process — fresh context, fresh worktree, isolated logs, clean exit codes. The skill-as-orchestrator pattern (one session, internal loop) accumulates context within a session and doesn't preserve fresh-context isolation. For autonomous cadence, compose with /loop: /loop 30m node scripts/ralph-loop.mjs --filter "tag=bug-fix".


Step 1 — Resolve the filter

Determine what subset of the queue to drain.

If $ARGUMENTS is non-empty, parse it as a filter expression. Supported keys:

Key Effect
tag=<value> Items whose tags field contains <value> (substring)
type=<value> Items with this exact type
priority=<value> Items at this priority (high, medium, low)
parentId=<uuid-or-prefix> Only direct children of this container
ancestorId=<uuid-or-prefix> Only items anywhere in this ancestor's subtree, any depth — broader than parentId. Used for the queue preview in Step 3; see the note below Step 1 on where it does and doesn't reach.

Multiple keys combine with AND (space-separated). Examples: tag=bug-fix priority=high, type=quick-fix, parentId=89d02e32, ancestorId=<projectRootId>.

Read the full file on GitHub · 332 lines

Files

What ships with it

1 file 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. 4d ago First seen · 332 lines · 99 tokens per session scan A 1273b937b612

Subscribe to this mod's changes

ralph is a skill published in the GitHub repository jpicklyk/task-orchestrator (205 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 4,995 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.