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 skills add fledgeling-co/fledgeling-plugins --skill tui-craftgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/tui-craft)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/tui-craft"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/tui-craft/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/fledgeling-co/fledgeling-plugins/tui-craft"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/tui-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00281 | $0.05013 |
| Opus 5.5 | $0.00112 | $0.02005 |
| Sonnet 5.5 | $0.00056 | $0.01003 |
| Haiku 4.5 | $0.00028 | $0.00501 |
Grade A, and why
tui-craft 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tui-craft
A terminal is a grid of cells, and almost every real TUI defect is arithmetic on that grid going wrong. A string template does not tell you how many cells it occupies. So reading the source tells you what the program intends to draw, never what it draws — and the gap between those two is where the bugs live.
This skill closes that gap with an instrument. You capture the running app into a typed cell grid, and every claim you make about how it looks refers to that grid. Build and review are the same loop; they differ only in who wrote the app.
Using Gemini? Read gemini.md for this skill's task-specific calibration and artifact checks. Its older runs do not establish Gemini 3.8 capability limits: preserve the user's selected implementation lane, and apply a model-specific route only when the current model or an observed failure supports it.
The rule that makes the rest work
A claim about a screen needs a captured frame. Not the source, not a
description, not a mock you sketched in a fenced code block. If capture fails,
that failure is the result you report — capture blocked, with what you tried.
It is never a reason to fall back on reading the code and saying it looks right.
This is worth holding even when it feels pedantic, because the failure mode it
prevents is specific and common: the model reads its own string template, does
the column arithmetic in its head, gets len("🚀 Deploy") == 8 instead of 9,
and declares a layout valid that renders with a torn border. Its predecessor
skill shipped 4,900 lines of sound design advice and had no way to see a single
pixel of what it produced.
Two frame kinds, and only one of them is evidence:
captured— produced byscripts/tui_capture.py(or by a framework snapshot test piped throughscripts/frame_from_ansi.py). Carries provenance: command, size,TERM, parser, a hash of the raw bytes, the child's exit code, and what the program did to the terminal.mock— anything you drew by hand. Useful for proposing a layout, and it may never support a finding. Label it, and say so when you show it.
What ships with it
9 files 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.
- 1mo ago Changed · +4 tokens per session 39a28880097d
- 1mo ago First seen · 369 lines · 277 tokens per session scan A 2534c6ab2c7b
tui-craft is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 281 tokens to every session and 5,013 once invoked, about $0.0011 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 2026-09-04.
Other skills, from other repositories
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
health
Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.
hunt
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.
think
Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.