AgentStack
SKILL verified MIT Self-run

Auto Ralph Submit

skill-dbinky-dbinky-skill-set-auto-ralph-submit · by dbinky

Non-interactive submission to ralph-o-matic with sensible defaults — pre-flight checks, auto-commit, auto-push, and Teams notification

No reviews yet
0 installs
13 views
0.0% view→install

Install

$ agentstack add skill-dbinky-dbinky-skill-set-auto-ralph-submit

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Auto Ralph Submit? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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:

``bash git add -A git commit -m "chore: pre-ralph cleanup" ``

  1. Branch pushed to origin — push if the branch isn't tracked remotely or has unpushed commits:

``bash BRANCH=$(git branch --show-current) git push -u origin "$BRANCH" ``

  1. Server reachable — check with ralph-o-matic status. If unreachable, notify Teams and stop.
  1. 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"}

Capture the job ID from the output.

Step 5: Notify Teams

ralph-o-matic notify --message "Ralph started for {SLUG} on branch {BRANCH} — Job #{JOB_ID}, {MAX_ITERATIONS} max passes. Dashboard: {SERVER_URL}/jobs/{JOB_ID}"

Step 6: Report

Output to the user/calling skill:

Submitted to Ralph-o-matic:
  Job ID:         #{JOB_ID}
  Branch:         {BRANCH}
  Priority:       {PRIORITY}
  Max Iterations: {MAX_ITERATIONS}
  Mode:           {local repo | cloned workspace}
  Dashboard:      {SERVER_URL}/jobs/{JOB_ID}

Error Handling

On ANY failure:

  1. Send Teams notification with error details via ralph-o-matic notify
  2. Output the error
  3. Stop — do not retry

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.