Borrowing it
Nothing to install: this file belongs to stevengonsalvez/agents-in-a-box. 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/stevengonsalvez/agents-in-a-box/main/.claude/skills/tmux-ui-tripwire/SKILL.mdgit clone --depth 1 https://github.com/stevengonsalvez/agents-in-a-boxWrote 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/stevengonsalvez/agents-in-a-box/tmux-ui-tripwire)<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/tmux-ui-tripwire"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/tmux-ui-tripwire/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/stevengonsalvez/agents-in-a-box/tmux-ui-tripwire"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/tmux-ui-tripwire.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00185 | $0.02271 |
| Opus 5 | $0.00093 | $0.01136 |
| Sonnet 5 | $0.00037 | $0.00454 |
| Haiku 4.5 | $0.00018 | $0.00227 |
Grade A, and why
tmux-ui-tripwire 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 12d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tmux-ui-tripwire
Overview
Tripwire tests drive the real ainb TUI binary in a detached tmux session, send keystrokes, capture the pane, and assert on rendered output. They are the ONLY tests that catch user-visible regressions the unit tests miss (e.g. plugin pipeline broken but cargo test green).
When to use this skill
- Writing a new
tripwire_*.rstest - An existing tripwire fails and the cause isn't obvious from
cargo testoutput - Tightening a tripwire whose assertions look weak (substring-OR on chrome strings)
- Diagnosing why a plugin "spawns but doesn't render"
Quick start — minimal viable tripwire
// crates/ainb-core/tests/tripwire_<feature>.rs
use std::path::PathBuf;
use std::process::Command;
use std::time::{Duration, Instant};
// 1. Skip gracefully if env can't support the test.
fn tmux_available() -> bool { /* see references/helpers.md */ }
fn ainb_bin() -> PathBuf { PathBuf::from(env!("CARGO_BIN_EXE_ainb")) }
#[test]
fn feature_renders_after_pressing_x() {
if !tmux_available() { eprintln!("SKIP: tmux"); return; }
// 2. Isolated HOME — seed onboarding.toml to skip wizard.
let home = tempfile::tempdir().unwrap();
seed_isolated_home(home.path());
// 3. Launch ainb tui in detached tmux session.
let session = format!("tripwire-{}", std::process::id());
Command::new("tmux").args(["new-session","-d","-s",&session,"-x","180","-y","50"]).status().unwrap();
let cmd = format!("HOME={} AINB_DISABLE_PLUGINS=1 exec {} tui",
home.path().display(), ainb_bin().display());
Command::new("tmux").args(["send-keys","-t",&session,&cmd,"Enter"]).status().unwrap();
// 4. Wait for HomeScreen — poll, don't bare-sleep.
let pre = poll_capture(&session, Instant::now() + Duration::from_secs(45),
|c| c.contains("Stats") && c.contains("[i]")).expect("HomeScreen never rendered");
// 5. Pre-press negative assertion — confirm we're not already on target screen.
assert!(!pre.contains("Usage Analytics"));
// 6. Send key WITHOUT Enter (single-char nav).
Command::new("tmux").args(["send-keys","-t",&session,"x"]).status().unwrap();
// 7. Post-press: positive marker AND negative placeholder.
let post = poll_capture(&session, Instant::now() + Duration::from_secs(30),
|c| c.contains("Expected Chrome") && !c.contains("Loading placeholder"))
.unwrap_or_else(|| capture_pane(&session));
Command::new("tmux").args(["kill-session","-t",&session]).status().ok();
assert!(post.contains("Expected Chrome"), "feature chrome never rendered:\n{post}");
assert!(!post.contains("Loading placeholder"), "stuck on placeholder:\n{post}");
}
What ships with it
5 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.
- 12d ago First seen · 126 lines · 185 tokens per session scan A 6b7790e6b8b5
tmux-ui-tripwire is a skill published in the GitHub repository stevengonsalvez/agents-in-a-box (23 stars, last pushed today), licensed MIT. It adds 185 tokens to every session and 2,271 once invoked, about $0.0009 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
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
test-case-to-katalon-studio
Convert Katalon True Platform/TestOps manual test cases into Katalon Studio automation inside a local Studio Test Project checkout. Use when you need to author or extend a .tc test case file and its paired Groovy script under Scripts/, keep test case variable GUIDs consistent with the .ts test suite bindings that read…
true-platform-testing
End-to-end Katalon True Platform testing workflow and lifecycle router. Use when one request spans several stages and no single skill owns all of it, for example analyze a requirement, design and import the cases, build a suite, run it with AI, and report the outcome. Also use to route any testing request across the…
playwright-execute
Run Playwright tests or suites and upload the resulting report to Katalon True Platform. Use when you need to execute Playwright scripts, package scripts, spec files, projects, or suites, configure or verify @katalon/playwright-reporter, upload Playwright reports with Katalon CLI/reporter commands, and verify uploaded…
test-case-to-playwright
Convert Katalon True Platform/TestOps manual test cases, test suites, or requirement-linked cases into Playwright TypeScript automation. Use when you need to fetch/read Katalon Platform test cases and implement Playwright scripts, create or adapt a Playwright framework, apply Page Object Model and fixtures, or…