agentmods.dev

ralph-run

ralph-run is a skill for Claude Code from rubenmarcus/ralph-starter. It costs 11 tokens per session (205 once invoked), scanned A, original, MIT.

An automated coding loop that reads specifications or a task, writes code, checks the result, and repeats until the work is complete.

In plain words
What is it for?
Running one-off coding tasks or planned work from GitHub, Linear, Notion, or Figma, with optional tests, linting, builds, and commits between iterations.
Why use it?
It reduces the manual back-and-forth of implementing a task, running checks, and making follow-up fixes.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the ralph-starter plugin — 11 skills, 1 agent shipped together

not rated 106repo 1mo ago A scan SkillSpector: pass 11 tokens original MIT

Good fit Running one-off coding tasks or planned work from GitHub, Linear, Notion, or Figma, with optional tests, linting, builds, and commits between iterations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rubenmarcus/ralph-starter/ralph-run
View source ↗ rubenmarcus/ralph-starter ralphstarter.ai
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.

Any agent
npx skills add rubenmarcus/ralph-starter --skill ralph-run
Clone the repo
git clone --depth 1 https://github.com/rubenmarcus/ralph-starter

Made for: Claude Code.

Or install ralph-starter, the plugin that ships this one along with the rest of its 11 skills, 1 agent.

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-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/rubenmarcus/ralph-starter/ralph-run.svg)](https://agentmods.dev/skills/rubenmarcus/ralph-starter/ralph-run)
Your own site
<a href="https://agentmods.dev/skills/rubenmarcus/ralph-starter/ralph-run"><img src="https://agentmods.dev/badge/skills/rubenmarcus/ralph-starter/ralph-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 205 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00011 $0.00205
Opus 5 $0.00005 $0.00102
Sonnet 5 $0.00002 $0.00041
Haiku 4.5 $0.00001 $0.00020

Measured 8d ago against content hash a74461f25e80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ralph-run 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 8d 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.

skills/ralph-run/SKILL.md · 19 lines

What it actually says

Run an autonomous coding loop using ralph-starter.

  1. Use the ralph_status tool to check the current project state
  2. Use ralph_run with the current project path to start the loop
    • Set auto: true for fully automated mode
    • Set commit: true to auto-commit changes
    • Set validate: true to run tests/lint/build between iterations
  3. The agent will iterate until the task is complete: read specs, write code, validate, commit, repeat

Options:

  • Specify task for a one-off task, or let it read from IMPLEMENTATION_PLAN.md
  • Use from to fetch specs from integrations: github, linear, notion, figma
  • Use project and label to filter issues from GitHub or Linear
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. 8d ago First seen · 19 lines · 11 tokens per session scan A a74461f25e80

Subscribe to this mod's changes

ralph-run is a skill published in the GitHub repository rubenmarcus/ralph-starter (106 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 205 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.

Building agentsClaude Codeaiai-agentsai-developer-toolscodex-cligithub
Related

Other skills, from other repositories

create-pr

Create GitHub pull requests with Conventional Commits-formatted titles and structured PR bodies. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.

yunseo-kim/agent-toolbox · 46 tokens

github-recon

Scan Git repositories, GitHub organizations, and source code for leaked secrets, API keys, credentials, and sensitive data. Use when analyzing source code security, when checking for credential exposure, or when the user mentions secret scanning or credential leaks.

zebbern/termstack · 52 tokens

pr-writer

ALWAYS use this skill when creating or updating pull requests — never create or edit a PR directly without it. Follows Sentry conventions for PR titles, descriptions, and issue references. Trigger on any create PR, open PR, submit PR, make PR,...

zebbern/termstack · 56 tokens

git-workflow

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…

Galaxy-Dawn/claude-scholar · 64 tokens

daily-paper-generator

Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.

Galaxy-Dawn/claude-scholar · 47 tokens

mongodb-query-optimizer

Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…

fcakyon/claude-codex-settings · 98 tokens