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 cbusillo/code --skill test-tuigit clone --depth 1 https://github.com/cbusillo/codeWrote 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/cbusillo/code/test-tui)<a href="https://agentmods.dev/skills/cbusillo/code/test-tui"><img src="https://agentmods.dev/badge/skills/cbusillo/code/test-tui/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/cbusillo/code/test-tui"><img src="https://agentmods.dev/badge/skills/cbusillo/code/test-tui.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 | $0.00043 | $0.02027 |
| Opus 5.5 | $0.00017 | $0.00811 |
| Sonnet 5.5 | $0.00009 | $0.00405 |
| Haiku 4.5 | $0.00004 | $0.00203 |
Grade A, and why
test-tui 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test TUI
This is a repo-local Every Code skill, not a generic TUI testing guide. Use it
for the Every Code TUI, the code command, and this repository's Rust
workspace. The just codex recipe name is a compatibility-era repo target, so
prefer direct code-rs commands when validating Every Code TUI changes.
You can start and use the Every Code TUI to verify changes.
Important Notes
- Start interactively.
- Always set
RUST_LOG="trace"when starting the process. - Pass
-c log_dir=<some_temp_dir>so logs are written to a known location. - When sending a test message programmatically, send text first, then send Enter in a separate write. Do not send text plus Enter in one burst.
- Use the Every Code TUI binary from the repo root:
cargo run --manifest-path code-rs/Cargo.toml -p code-tui -- -c log_dir=<some_temp_dir>.
Visibility Contract
Do not claim that you visually verified the live TUI unless you actually used a
live terminal surface that exposed the rendered UI. A rebuilt code binary,
passing tests, log inspection, Code Bridge events, and embedded string checks are
useful evidence, but they are not live visual verification by themselves.
Code Bridge may capture browser/app surfaces, console logs, pageviews, or bridge screenshots when a client is connected. It does not prove that the current terminal TUI pixels were visible unless a screenshot or control response clearly comes from the TUI surface being tested.
Use precise language in closeout:
live TUI visually verifiedonly after direct TUI capture/interaction.iTerm2 session verifiedafter reading the relevant iTerm2 session's live terminal contents through an explicit iTerm2 capture helper.macOS window screenshot verifiedafter capturing the targeted window or rectangle pixels and inspecting the image.VT100-render verifiedafter the snapshot harness renders the relevant frame.binary/restart verifiedaftercode --version, PATH target, and process restart checks pass.not visually verifiedwhen you only have tests/logs/binary evidence.
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.
- 1mo ago First seen · 212 lines · 43 tokens per session scan A 70c2d8275585
test-tui is a skill published in the GitHub repository cbusillo/code (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,027 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
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.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
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.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.