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.
npx agentmods add skills/abdelstark/worldforge/tui-developmentnpx skills add AbdelStark/worldforge --skill tui-developmentgit clone --depth 1 https://github.com/AbdelStark/worldforgeWhat 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 | $0.00063 | $0.00693 |
| Opus 5 | $0.00032 | $0.00347 |
| Sonnet 5 | $0.00013 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
tui-development 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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TUI Development
Architecture Boundary
src/worldforge/harness/robotics_launch.py: launcher and host-owned viewer helpers.src/worldforge/harness/robotics_view.py: Textual-free robotics report model and constants.src/worldforge/harness/robotics_tui_rendering.py: pure Rich renderable builders for panes.src/worldforge/harness/tui.py: robotics-showcase-only Textual import surface.src/worldforge/harness/tui_styles.pyandtui_robotics_styles.py: Textual CSS constants.
Never import Textual from worldforge.__init__, worldforge.cli, or non-TUI harness modules.
Robotics TUI Engineering Contract
- Treat the robotics showcase as a testable report renderer first and a Textual screen second.
- Keep robotics summaries and screen state JSON-native so evidence can move between CLI, tests, screenshots, and docs.
- Keep long-running optional runtime work behind explicit commands; UI state should report progress and failure without hiding the underlying exception context.
- The removed world-creation/provider/eval/benchmark harness screens must not come back through this skill. Use CLI/docs surfaces for those workflows.
Workflow
- Read
robotics_view.py,robotics_tui_rendering.py,robotics_launch.py, andtui.pybefore touching TUI modules. - Keep all Textual imports inside
harness/tui.py. - Keep report rendering pure and deterministic outside Textual so tests can run without the
harnessextra. - Update the relevant tests:
test_robotics_tui_rendering.py,test_robotics_showcase.py,test_robotics_showcase_scripts.py, or focused harness report tests. - Update screenshots only when UI behavior or documented visual state changed.
- Validate with focused robotics tests, optional-import boundary checks, and the
--extra harnesscoverage gate when behavior changes.
Definition Of Done
- Robotics report rendering works without the
harnessextra. - Changed robotics UI behavior is covered at the pure-rendering level before TUI-specific tests.
- Textual imports remain isolated and optional-import boundary checks pass when imports moved.
- Snapshot or screenshot updates are intentional and tied to verified behavior.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 59 lines · 63 tokens per session scan A 7733ebf40a9d
tui-development is a skill published in the GitHub repository AbdelStark/worldforge (108 stars, last pushed 23d ago), licensed MIT. It adds 63 tokens to every session and 693 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
wellbeing
Proactive coaching across hydration, breaks, meals AND posture. Use when an [activity] event fires (message starts with [activity] Activity detected: . — labels include drink, break, celebrate, the fatigue label "yawning", or sedentary raw labels like "using computer"; sedentary events may also carry a…
faq
Explain how to run and use this repository's local Web UI, with detailed guidance for every Settings section and its visible controls. Use for questions about web development, Monitor, Setup, or Settings.
computer-use
Control the user's Mac via the paired Autonomous Buddy companion app — open/close apps, navigate URLs in Chrome, type text into focused fields, fire keyboard shortcuts, show desktop notifications, write to clipboard, click named UI buttons via macOS Accessibility. Also covers vision-driven tasks (screenshot…
connectors
Detect which third-party connectors (Gmail, Google Calendar, Google Drive, Notion, Figma, Asana, Linear, GitHub, Ahrefs, …) are connected to this device, and use them to answer or act for the user. Use when the user asks what's connected ("what connectors do I have", "is my gmail connected", "did I link figma"), or…
mood
Tracks the USER's mood only — signals + synthesized decision from camera/voice/telegram. Do NOT use for emotion commands directed at the device ("show sad", "be happy", bare "sad now"); those go through emotion/SKILL.md and are never logged here. Music/wellbeing skills consume the latest decision.
sensing-track
Query flow event logs to answer questions about past sensing events — "Have you seen anybody between 10pm and 12pm?", "Is there any motion in the last hour?", "What happened while I was away?".