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.
Borrowing it
Nothing to install: this file belongs to subsy/ralph-tui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/subsy/ralph-tui/main/.agents/skills/testing-tui-runtime/SKILL.mdgit clone --depth 1 https://github.com/subsy/ralph-tuiWrote 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/testing-tui-runtime)<a href="https://agentmods.dev/skills/subsy/ralph-tui/testing-tui-runtime"><img src="https://agentmods.dev/badge/skills/subsy/ralph-tui/testing-tui-runtime/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/subsy/ralph-tui/testing-tui-runtime"><img src="https://agentmods.dev/badge/skills/subsy/ralph-tui/testing-tui-runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 25 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00047 | $0.02770 |
| Opus 5.5 | $0.00019 | $0.01108 |
| Sonnet 5.5 | $0.00009 | $0.00554 |
| Haiku 4.5 | $0.00005 | $0.00277 |
Grade A, and why
testing-tui-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime/E2E testing of the ralph-tui TUI
Use this when a change must be proven in the real TUI (watch mode, engine status labels, pause/resume, shutdown/quit paths) rather than with unit tests.
Build & run
cd /path/to/ralph-tui && bun run build # produces dist/cli.js
Run the built CLI (not bun run dev) so behaviour matches shipped code:
bun /path/to/ralph-tui/dist/cli.js run [flags]
Scratch tracker (never touch the repo's own .beads)
Create a throwaway project dir with its own beads store and drive scenarios with bd:
export RALPH_TEST_DIR="$(mktemp -d "${TMPDIR:-/tmp}/ralph-tui-run.XXXXXX")" && cd "$RALPH_TEST_DIR"
bd init # or `bd create ...` which bootstraps the store
bd create "Watch mode epic" --type epic -p 1 # note the epic id bd prints
bd create "Alpha task" --type task -p 2 --parent <epic-id>
A fresh dir per run, not a fixed one: a reused dir carries over .beads tasks, the
.ralph-tui session file, locks and guards — exactly the things most scenarios here assert on, so
a Recovered stale session banner or a stale-lock prompt from the previous run reads as a
finding of the build under test. The unique dir also gives the run a unique epic id, which is how
you address its process (see the signal trap below).
Gotchas:
bdcommands must be run with the scratch dir as the working directory, otherwise you get "no beads database found".- With
--tracker beads, the TUI requires--epic <id>; without it the TUI shows "No epics found" and interactive epic selection blocks automation. br(beads-rust) may not be installed even though AGENTS.md references it;bdworks.
Fake agents (no AI credentials needed)
Put plugins in ~/.config/ralph-tui/plugins/agents/:
echo.ts— returnsecho-agent: local fake response\n<promise>COMPLETE</promise>instantly.slowecho.ts— same but sleeps ~25s in interruptible 500 ms chunks. Essential for testing quit/pause mid-iteration; an instant agent gives you no window to interrupt.
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.
- 1mo ago First seen · 164 lines · 47 tokens per session scan A 2eaaa09440b4
testing-tui-runtime is a skill published in the GitHub repository subsy/ralph-tui (2,459 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,770 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.