What is tui-smoke-test-with-tmux?

A smoke-testing workflow for ACN’s interactive terminal interface, which is a text-based screen controlled from a terminal window. It runs the real program in tmux, sends key presses, captures screens as text, and checks error output.

Use it after changing ACN’s terminal interface, input handling, help or status text, or interactive command-line behavior.

It catches interaction and display problems that ordinary automated tests may miss. The captured terminal states can also be used to create focused regression tests for particular user flows.

How FTShare-Lab/agent-claim-network configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to FTShare-Lab/agent-claim-network. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/FTShare-Lab/agent-claim-network/main/.agents/skills/tui-smoke-test-with-tmux/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/FTShare-Lab/agent-claim-network

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ftshare-lab/agent-claim-network/tui-smoke-test-with-tmux/github.svg)](https://agentmods.dev/skills/ftshare-lab/agent-claim-network/tui-smoke-test-with-tmux)

Your own site

<a href="https://agentmods.dev/skills/ftshare-lab/agent-claim-network/tui-smoke-test-with-tmux"><img src="https://agentmods.dev/badge/skills/ftshare-lab/agent-claim-network/tui-smoke-test-with-tmux/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ftshare-lab/agent-claim-network/tui-smoke-test-with-tmux"><img src="https://agentmods.dev/badge/skills/ftshare-lab/agent-claim-network/tui-smoke-test-with-tmux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,879 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00108	$0.01879
Opus 5	$0.00054	$0.00940
Sonnet 5	$0.00022	$0.00376
Haiku 4.5	$0.00011	$0.00188

Measured 11d ago against content hash d9e4503e2c87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tui-smoke-test-with-tmux 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 11d ago.

The scan reads SKILL.md. This mod also ships 14 executable files (scripts/shared_mcp_real_llm_fixture.sh, scripts/tui_tmux_background_shell_real_llm.sh, scripts/tui_tmux_compact_queue_escape_regression.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/tui-smoke-test-with-tmux/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TUI Smoke Test With tmux

Use this skill to validate the real terminal behavior of the Agent Claim Network TUI. It supports both the default smoke test and task-specific tmux scripts for user-described interaction flows.

The project TUI entrypoint is:

cargo run --quiet --bin acn -- --config config.toml

The TUI uses ratatui + crossterm, so verify it in a real tty. Prefer tmux capture files over screenshots because they can be inspected with rg, sed, and diffs.

The bundled runners that inspect TOML config use Python's standard library and require Python 3.11+ (tomllib). Their shared preflight reports this requirement before starting a TUI.

Workflow

Review the TUI change and decide the expected screen states or key flow.
Ensure tmux is installed. If an environment or dependency is missing, fix that environment issue first.
Source export_env.sh before verification when it exists or the run needs API/model variables.
For broad startup verification, run the bundled smoke script from the repo root:

.agents/skills/tui-smoke-test-with-tmux/scripts/tui_tmux_smoke.sh

For a specific user story, write a focused script using scripts/tui_tmux_lib.sh; use an existing regression script as the structural example.
Inspect the generated *.txt captures and stderr.log; use exact text assertions where stable.

Focused Verification

When the user asks whether a concrete TUI behavior is fixed, do not rely only on the default /help smoke test. Convert the behavior into a tmux flow:

Name the flow after the behavior, for example queue-cancel-resend.
Define checkpoints: initial, queued, after_cancel, after_resend, etc.
At each checkpoint, capture the pane to a task-specific directory under target/.
Assert stable visible markers with rg; avoid brittle assertions on session ids, timing-dependent model output, or full-screen whitespace.
Always assert stderr.log is empty and the tmux session is cleaned up.

Read the full file on GitHub · 168 lines

Files

What ships with it

15 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.

Changes

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.

11d ago First seen · 168 lines · 108 tokens per session scan A d9e4503e2c87

Subscribe to this mod's changes

tui-smoke-test-with-tmux is a skill published in the GitHub repository FTShare-Lab/agent-claim-network (41 stars, last pushed 2d ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,879 once invoked, about $0.0005 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.

Debugging E2E testing LLM Rust Testing ai-agents knowledge-sharing mcp multi-agent-systems

reproduce-bug

Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…

googleapis/mcp-toolbox · 130 tokens

qa-expert

Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.

personamanagmentlayer/pcl · 53 tokens

agent-claim-network: Skill for Codex