auto-ralph-submit

auto-ralph-submit is a skill for Claude Code, Codex from dbinky/dbinky-skill-set. It costs 35 tokens per session (780 once invoked), scanned A, original, MIT.

A command that submits an existing RALPH.md work plan to ralph-o-matic for repeated refinement. RALPH.md is a repository file containing the work plan expected by that system.

In plain words
What is it for?
Use it when RALPH.md already exists and you want to submit the repository for iterative refinement with a chosen priority, iteration limit, and optional feature label.
Why use it?
It automates the checks and submission steps, including committing local changes, pushing the branch, and notifying Teams.

Skill for Claude CodeCodex

Part of the pr-review plugin — 8 skills, 15 agents 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/dbinky/dbinky-skill-set/auto-ralph-submit
Any agent
npx skills add dbinky/dbinky-skill-set --skill auto-ralph-submit
Clone the repo
git clone --depth 1 https://github.com/dbinky/dbinky-skill-set

Made for: Claude Code, Codex.

Or install pr-review, the plugin that ships this one along with the rest of its 8 skills, 15 agents.

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 auto-ralph-submit

README.md
[![agentmods](https://agentmods.dev/badge/skills/dbinky/dbinky-skill-set/auto-ralph-submit.svg)](https://agentmods.dev/skills/dbinky/dbinky-skill-set/auto-ralph-submit)
Your own site
<a href="https://agentmods.dev/skills/dbinky/dbinky-skill-set/auto-ralph-submit"><img src="https://agentmods.dev/badge/skills/dbinky/dbinky-skill-set/auto-ralph-submit.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 780 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 5.1 $0.00035 $0.00780
Opus 5 $0.00017 $0.00390
Sonnet 5 $0.00007 $0.00156
Haiku 4.5 $0.00003 $0.00078

Measured 5d ago against content hash a677ce3bb261, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

auto-ralph-submit 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 5d 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/auto-ralph-submit/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Ralph Submit

You are submitting work to ralph-o-matic for iterative refinement with zero user interaction. This skill expects a RALPH.md file to already exist in the repository root (generated by auto-ralph-prep or plan-to-ralph).

Arguments

Parse the following from the user's command or calling skill:

  • --priority LEVEL: Job priority — high, normal, low (default: high)
  • --max-iterations N: Max ralph passes (default: 1000)
  • --local: Use local repo directory (default: true)
  • --slug SLUG: Feature slug for notification messages (optional)

Workflow

Execute these steps in order. Do not ask for user input at any point.

Step 1: Validate RALPH.md Exists

Check for RALPH.md in the repository root. If missing, send a Teams notification and stop:

ralph-o-matic notify --message "Pipeline failed: RALPH.md not found in $(git remote get-url origin) on branch $(git branch --show-current). Run /auto-ralph-prep first."

Step 2: Pre-flight Checks

Run these checks before submission:

  1. Working tree clean — if uncommitted changes exist, stage and commit them:

    git add -A
    git commit -m "chore: pre-ralph cleanup"
    
  2. Branch pushed to origin — push if the branch isn't tracked remotely or has unpushed commits:

    BRANCH=$(git branch --show-current)
    git push -u origin "$BRANCH"
    
  3. Server reachable — check with ralph-o-matic status. If unreachable, notify Teams and stop.

  4. Branch not already in queue — check via the API. If already queued, notify Teams and stop.

Step 3: Detect Local Mode

Read the configured server URL from ralph-o-matic config. If the server is localhost/127.0.0.1 and --local was not explicitly set to false, use local mode:

LOCAL_DIR=$(git rev-parse --show-toplevel)

If the server is NOT local, skip local mode — remote servers can't access local paths.

Step 4: Submit

ralph-o-matic submit \
    --priority {PRIORITY} \
    --max-iterations {MAX_ITERATIONS} \
    ${LOCAL_DIR:+--working-dir "$LOCAL_DIR"}

Read the full file on GitHub · 98 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. 5d ago First seen · 98 lines · 35 tokens per session scan A a677ce3bb261

Subscribe to this mod's changes

auto-ralph-submit is a skill published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 780 once invoked, about $0.0002 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.