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 agentmods add skills/libtmux/libtmux-go/testing-the-mcp-servernpx skills add libtmux/libtmux-go --skill testing-the-mcp-servergit clone --depth 1 https://github.com/libtmux/libtmux-goWrote 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/libtmux/libtmux-go/testing-the-mcp-server)<a href="https://agentmods.dev/skills/libtmux/libtmux-go/testing-the-mcp-server"><img src="https://agentmods.dev/badge/skills/libtmux/libtmux-go/testing-the-mcp-server.svg" alt="Measured on agentmods" 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 | $0.00145 | $0.01915 |
| Opus 5 | $0.00072 | $0.00958 |
| Sonnet 5 | $0.00029 | $0.00383 |
| Haiku 4.5 | $0.00015 | $0.00192 |
Grade A, and why
testing-the-mcp-server 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 5d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing the MCP server
go test ./... proves the handlers. It does not prove that a client can
discover a tool, get past an approval gate, call it with arguments a model
would actually send, and survive cancelling it mid-flight. Those failures live
in the gap between the in-memory transport the Go tests use and a real process
speaking JSON-RPC over a pipe.
One socket, chosen once
The Python server takes socket_name on every targeted tool, so a client picks
the tmux per call. This one does not: an operator picks the socket at launch
and a client reaches only that socket.
$ libtmux-mcp -socket-name mcp-target
LIBTMUX_SOCKET names it when no flag does, matching the Python server, so one
configuration serves both. A flag wins over the variable. Ask the server which
it took rather than assuming — -doctor names the origin:
$ libtmux-mcp -doctor
Three tmux servers, never one
| Role | Socket | Who touches it |
|---|---|---|
| The real session | default | a person, interactively — never a test |
| Harness | tmux -L cli-harness |
the driver, sending keys to a CLI's TUI |
| Target | tmux -L mcp-target |
the server under test, via -socket-name |
Keeping the target apart from the harness is the load-bearing part: a destructive tool call on the socket hosting the agent's own TUI tears down the agent mid-test, and its redraws pollute every capture.
Give the whole run its own root so a sibling checkout's suite cannot end a server this one is using:
$ export TMUX_TMPDIR=/tmp/libtmux-go-probe && mkdir -p "$TMUX_TMPDIR" && unset TMUX TMUX_PANE
Climb only as high as the question needs
Layer 0 — the real binary over raw JSON-RPC
Fastest and most deterministic, it covers process boundaries the Go tests do
not: framing, protocol negotiation, and the environment a client actually
supplies. references/drive.py is that driver:
it spawns the binary with an environment it builds rather than inherits, holds
stdin open, matches replies by id, declines any question the server asks, and
reads a plan of JSON-RPC calls from stdin.
What ships with it
3 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.
- 5d ago First seen · 189 lines · 145 tokens per session scan A 1a06e02ee6e3
testing-the-mcp-server is a skill published in the GitHub repository libtmux/libtmux-go (0 stars, last pushed 6d ago), licensed MIT. It adds 145 tokens to every session and 1,915 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
aoe
Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.
aoe
Manage AI coding agent sessions via Agent of Empires (aoe).
gui-onboarding-verification-skill
GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…
gui-integration-test
GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…
gui-integration-test-video
GUI desktop app only. Run and author Warp Rust integration tests (the crates/integration harness) that capture screenshots and video via TestStep::withstartrecording() / withtakescreenshot(), including mouse and keyboard event overlays. TRIGGER only for the integration-test recording pipeline: recording or…
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.