Ralph TUI is a terminal interface that repeatedly sends tasks from a task tracker to AI coding agents, monitors their work, and moves through the list autonomously. Developers use it to run agents such as Claude Code, Codex, Cursor CLI, or Gemini CLI across ordered tasks, with persistence and progress visibility; catalogue entries add skills and instructions for that workflow.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/subsy/ralph-tuinpx agentmods add skills/subsy/ralph-tui/ralph-tui-create-jsonWrote 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.
[](https://agentmods.dev/skills/subsy/ralph-tui/ralph-tui-create-json)<a href="https://agentmods.dev/skills/subsy/ralph-tui/ralph-tui-create-json"><img src="https://agentmods.dev/badge/skills/subsy/ralph-tui/ralph-tui-create-json.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 5.1 | $0.00057 | $0.02702 |
| Opus 5 | $0.00028 | $0.01351 |
| Sonnet 5 | $0.00011 | $0.00540 |
| Haiku 4.5 | $0.00006 | $0.00270 |
Grade A, and why
ralph-tui-create-json 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.
How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph TUI - Create JSON Tasks
Converts PRDs to prd.json format for ralph-tui autonomous execution.
Note: This skill is bundled with ralph-tui's JSON tracker plugin. Future tracker plugins (Linear, GitHub Issues, etc.) will bundle their own task creation skills.
⚠️ CRITICAL: The output MUST be a FLAT JSON object with "name" and "userStories" at the ROOT level. DO NOT wrap content in a "prd" object or use "tasks" array. See "Schema Anti-Patterns" section below.
The Job
Take a PRD (markdown file or text) and create a prd.json file:
- Extract Quality Gates from the PRD's "Quality Gates" section
- Parse user stories from the PRD
- Append quality gates to each story's acceptance criteria
- Set up dependencies between stories
- Output ready for
ralph-tui run --prd <path>
Step 1: Extract Quality Gates
Look for the "Quality Gates" section in the PRD:
## Quality Gates
These commands must pass for every user story:
- `pnpm typecheck` - Type checking
- `pnpm lint` - Linting
For UI stories, also include:
- Verify in browser using dev-browser skill
Extract:
- Universal gates: Commands that apply to ALL stories (e.g.,
pnpm typecheck) - UI gates: Commands that apply only to UI stories (e.g., browser verification)
If no Quality Gates section exists: Ask the user what commands should pass, or use a sensible default like npm run typecheck.
Output Format
The JSON file MUST be a FLAT object at the root level:
{
"name": "[Project name from PRD or directory]",
"branchName": "ralph/[feature-name-kebab-case]",
"description": "[Feature description from PRD]",
"userStories": [
{
"id": "US-001",
"title": "[Story title]",
"description": "As a [user], I want [feature] so that [benefit]",
"acceptanceCriteria": [
"Criterion 1 from PRD",
"Criterion 2 from PRD",
"pnpm typecheck passes",
"pnpm lint passes"
],
"priority": 1,
"passes": false,
"notes": "",
"dependsOn": []
},
{
"id": "US-002",
"title": "[UI Story that depends on US-001]",
"description": "...",
"acceptanceCriteria": [
"...",
"pnpm typecheck passes",
"pnpm lint passes",
"Verify in browser using dev-browser skill"
],
"priority": 2,
"passes": false,
"notes": "",
"dependsOn": ["US-001"]
}
]
}
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.
- 8d ago First seen · 387 lines · 57 tokens per session scan A 47c5da58a0c1
ralph-tui-create-json is a skill published in the GitHub repository subsy/ralph-tui (2,437 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 2,702 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…