PRD-driven persistence loop until task completion with verification. Activate when user says: ralph, don't stop, must complete, finish this, keep going until done.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Ralph
Ralph is a PRD-driven persistence loop that keeps working on a task until ALL user stories have `passes: true` and are reviewer-verified.
## When to Use
- Task requires guaranteed completion with verification
- Work may span multiple iterations and needs persistence
- Task benefits from structured PRD-driven execution
## When NOT to Use
- Full autonomous pipeline → use `/omg-autopilot`
- Explore or plan before committing → use `/plan`
- Quick one-shot fix → delegate to @executor
## Flags
- `--no-prd`: Skip PRD generation, work in legacy mode (for trivial fixes)
- `--no-deslop`: Skip the mandatory post-review cleanup pass
## Steps
### 1. PRD Setup (first iteration)
- Check if `.omc/prd.json` exists via `omg_read_prd`
- If none exists, generate a PRD scaffold with task-specific acceptance criteria
- **CRITICAL**: Replace generic criteria with specific, testable ones
- Initialize progress tracking
### 2. Pick Next Story
- Read PRD via `omg_read_prd`
- Select highest-priority story with `passes: false`
### 3. Implement Current Story
- Delegate to @executor at appropriate complexity level
- If sub-tasks are discovered, add as new stories to PRD
…
The line at the top of this page pins the label git:20260412.9d9ce51, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (2849 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
zereight/gitlab-mcp · 2,059 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jad7s4d26gqvc3zv
GET https://markdownregistry.com/api/v1/resolve?ref=zereight/gitlab-mcp/ralph
GET https://markdownregistry.com/api/v1/blob/49195a0d126efaab04551e781466351444fd7d523a992ccd6a4501575cee92f0
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
zereight/gitlab-mcp · .github/skills/ai-slop-cleaner/SKILL.md · Clean AI-generated code slop with regression-safe workflow. Activate when user says: deslop, anti-slop, AI slop…
zereight/gitlab-mcp · .github/skills/cancel/SKILL.md · Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill…
zereight/gitlab-mcp · .github/skills/deep-dive/SKILL.md · 2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive…
zereight/gitlab-mcp · .github/skills/deep-interview/SKILL.md · Socratic deep interview with mathematical ambiguity gating. Activate when user says: deep interview, interview me, ask…
zereight/gitlab-mcp · .github/skills/omg-autopilot/SKILL.md · Full autonomous execution from idea to working code. Activate when user says: autopilot, auto-pilot, autonomous, build…
zereight/gitlab-mcp · .github/skills/plan/SKILL.md · Strategic planning with optional interview workflow. Activate when user says: plan this, plan the, let's plan, make a…
zereight/gitlab-mcp · .github/skills/remember/SKILL.md · Promote reusable project knowledge to the right memory surface. Activate when user says: remember this, save this…
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/ralph/SKILL.md · Convert PRDs to prd.json format for the Ralph autonomous agent system
chainlesschain/chainlesschain · desktop-app-vue/src/main/ai-engine/cowork/skills/builtin/ralph/SKILL.md · Drive an approved plan to completion as a single persistent owner. Third step of the canonical coding workflow.
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/ralph/SKILL.md · Enforces Law 6 (Iterate Means One Thing) of the 7 Laws of AI Agent Discipline at PRD scale. Ralph is an autonomous AI…
