Borrowing it
Nothing to install: this file belongs to 0xku/kon. 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/0xku/kon/main/.agents/skills/kon-tmux-test/SKILL.mdgit clone --depth 1 https://github.com/0xku/konWrote 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/0xku/kon/kon-tmux-test)<a href="https://agentmods.dev/skills/0xku/kon/kon-tmux-test"><img src="https://agentmods.dev/badge/skills/0xku/kon/kon-tmux-test/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/0xku/kon/kon-tmux-test"><img src="https://agentmods.dev/badge/skills/0xku/kon/kon-tmux-test.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 | $0.00032 | $0.02958 |
| Opus 5.5 | $0.00013 | $0.01183 |
| Sonnet 5.5 | $0.00006 | $0.00592 |
| Haiku 4.5 | $0.00003 | $0.00296 |
Grade C, and why
kon-tmux-test scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/kon-test-project /tmp/kon-e2e-home How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kon Tmux E2E Testing
End-to-end testing of kon using tmux sessions to programmatically control the TUI application.
Why Tmux?
Kon is a TUI (Textual-based) app. Running tests programmatically is hard. Tmux provides:
tmux new-session- isolate test environmenttmux send-keys- send keyboard inputtmux capture-pane- capture outputtmux has-session- check if kon is running
Test Design Philosophy
- Deterministic: Shell scripts create reproducible test environments
- Isolated config: Tests run with
HOME=/tmp/kon-e2e-homeso runtime settings do not mutate the real user config; auth JSON files are copied into the temp HOME when present so provider startup still works - Separation of concerns: Shell script runs steps and captures output; kon/the reviewer evaluates results
- Output-based evaluation: Test success/failure determined by reading output files, not shell script heuristics
- UI-focused: Test triggers (
@,/, runtime pickers, keybindings) by checking UI elements appear - Filesystem verification: Tool execution is verified through files under
/tmp/kon-test-project
Quick Start
# Run all e2e tests from the repo root
bash .agents/skills/kon-tmux-test/run-e2e-tests.sh
# Optional: keep the temporary HOME for debugging
KEEP_E2E_HOME=1 bash .agents/skills/kon-tmux-test/run-e2e-tests.sh
# Optional: override launch command/provider/model
KON_CMD='uv run kon --model gpt-5.5' \
bash .agents/skills/kon-tmux-test/run-e2e-tests.sh
After running, read /tmp/kon-test-*.txt and evaluate the captured pane/config/filesystem outputs.
Test Scripts
Setup Script: setup-test-project.sh
Creates a deterministic test project structure at /tmp/kon-test-project/.
bash .agents/skills/kon-tmux-test/setup-test-project.sh
Main Test Script: run-e2e-tests.sh
Runs comprehensive e2e tests including UI triggers, runtime controls, tab completion, and tool execution.
bash .agents/skills/kon-tmux-test/run-e2e-tests.sh
What ships with it
2 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.
- 2mo ago First seen · 251 lines · 32 tokens per session scan C 2175f776386b
kon-tmux-test is a skill published in the GitHub repository 0xku/kon (356 stars, last pushed 26d ago), licensed MIT. It adds 32 tokens to every session and 2,958 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
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.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.