A task-execution loop driven by a product requirements document, or PRD: a written list of user stories and acceptance checks. It keeps working through unfinished stories until they pass verification.

It helps create or read a PRD, select the next unfinished story, delegate implementation, add newly discovered work, and verify each story before continuing.

It helps with tasks that need several implementation and review cycles, so progress is tracked against specific completion checks instead of a vague definition of done.

ralph — Skill by zereight

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/zereight/gitlab-mcp/ralph

Any agent

npx skills add zereight/gitlab-mcp --skill ralph

Clone the repo

git clone --depth 1 https://github.com/zereight/gitlab-mcp

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 688 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.

Model	Per session	Once invoked
Fable 5	$0.00036	$0.00688
Opus 5	$0.00018	$0.00344
Sonnet 5	$0.00007	$0.00138
Haiku 4.5	$0.00004	$0.00069

Measured 3d ago against content hash 49195a0d126e, 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 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 3d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

ralph — 100% identical, 0 lines differ
ralph — 92% identical, 2 lines differ

.github/skills/ralph/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

4. Verify Acceptance Criteria

For EACH criterion, verify with fresh evidence
Run relevant checks (test, build, lint, typecheck)
If any criterion NOT met, continue working

5. Mark Story Complete

Set passes: true via omg_update_story
Record progress in progress.txt

6. Check PRD Completion

Call omg_check_completion
If NOT all complete, loop to Step 2
If ALL complete, proceed to verification

7. Reviewer Verification

@verifier checks against specific acceptance criteria from PRD
@architect reviews for architectural soundness

7.5 Mandatory Cleanup Pass

Unless --no-deslop, run /ai-slop-cleaner on changed files only

7.6 Regression Re-verification

Re-run all tests after cleanup pass
Only proceed after regression tests pass

8. Completion

On approval: run /cancel for clean exit
On rejection: fix issues, re-verify, loop back

Read the full file on GitHub · 86 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.

3d ago First seen · 86 lines · 36 tokens per session scan A 49195a0d126e

Subscribe to this mod's changes

ralph is a skill published in the GitHub repository zereight/gitlab-mcp (1,939 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 688 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 2026-08-30.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens