Assistant: Skill for Claude Code

.claude/skills/mewbo-cli-smoketest/SKILL.md

mewbo-cli-smoketest is a skill for Claude Code from bearlike/Assistant. It costs 111 tokens per session (4,297 once invoked), scanned B, original, MIT.

A procedure for testing the Mewbo command-line interface from end to end in tmux. tmux provides a controllable terminal session for programs with interactive full-screen interfaces.

In plain words
What is it for?
Use it to smoke-test Mewbo, its agent loop, streaming interface, and related terminal features after changes.
Why use it?
It captures both what the terminal displays and what the program logs, making interface errors and regressions easier to detect.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions Claude Code.

This is bearlike/Assistant's own configuration. It tells Claude Code how to work on Assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Assistant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bearlike/Assistant. 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/bearlike/Assistant/master/.claude/skills/mewbo-cli-smoketest/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bearlike/Assistant

Made for: Claude Code.

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.

agentmods badge for mewbo-cli-smoketest

README.md
[![agentmods](https://agentmods.dev/badge/skills/bearlike/assistant/mewbo-cli-smoketest.svg)](https://agentmods.dev/skills/bearlike/assistant/mewbo-cli-smoketest)
Your own site
<a href="https://agentmods.dev/skills/bearlike/assistant/mewbo-cli-smoketest"><img src="https://agentmods.dev/badge/skills/bearlike/assistant/mewbo-cli-smoketest.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,297 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 241
    Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.
    Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
  • medium Excessive Agency · line 23
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 38
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 23
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 38
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.04297
Opus 5 $0.00056 $0.02148
Sonnet 5 $0.00022 $0.00859
Haiku 4.5 $0.00011 $0.00430

Measured 8d ago against content hash 598351e47c62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

mewbo-cli-smoketest scanned grade B 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 8d 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- **Env var expansion.** CWD `.mcp.json` may use `${VAR}`; if unset in the launching shell, tokens stay literal and MCP calls fail silently.
.claude/skills/mewbo-cli-smoketest/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mewbo CLI Smoke Test via Tmux

Automate end-to-end CLI testing by running mewbo inside a tmux pane, driving it with commands/queries, and analyzing both the rendered TUI frame and the verbose log for errors, warnings, and regressions.

Why tmux

The CLI is one full-screen Textual App, with live streaming + a per-agent fleet sidebar layered on top. You cannot run it via the Bash tool because it requires a PTY and renders interactive widgets on the alternate screen. Tmux gives you a real terminal to drive the app while capturing output programmatically.

Two capture channels (read this first)

A Textual app paints the alternate screen, so the two things you want to observe come from two different places:

  1. The rendered TUI frametmux capture-pane -p returns the current visible frame only. The alt-screen keeps no scrollback, so -S -100 does not give you history the way it does for a plain shell; it just returns the visible grid. To inspect what scrolled past, drive the app to re-render (e.g. scroll the transcript) or rely on the log channel below.
  2. The verbose log — route logs to a file so they don't corrupt the TUI, then grep the file. Do not use --log-console with the TUI (it paints over the widgets). Launch with:
tmux send-keys -t <session>:mewbo-test \
  "mewbo -vv --auto-approve --log-file /tmp/mewbo-test.log --log-overwrite" Enter

Then, after each step: tmux capture-pane -p -t <session>:mewbo-test for the frame, and grep -nE 'WARNING|ERROR|Traceback|Failed to' /tmp/mewbo-test.log for diagnostics. The two are complementary — a clean frame can still hide a logged reconnect error, and a busy log can accompany a correctly-rendered frame.

Use the installed mewbo (from uv tool install .) or uv run mewbo from the repo root. The installed binary tests what the user actually runs.

Setup

tmux list-sessions
tmux new-window -t <session>:<next> -n mewbo-test
# width matters: the sidebar/fleet only render legibly with enough columns
tmux resize-window -t <session>:mewbo-test -x 200 -y 50 2>/dev/null || true
tmux send-keys -t <session>:mewbo-test \
  "mewbo -vv --auto-approve --log-file /tmp/mewbo-test.log --log-overwrite" Enter
sleep 10 && tmux capture-pane -p -t <session>:mewbo-test

Read the full file on GitHub · 243 lines

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.

  1. 8d ago First seen · 243 lines · 111 tokens per session scan B 598351e47c62

Subscribe to this mod's changes

mewbo-cli-smoketest is a skill published in the GitHub repository bearlike/Assistant (42 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 4,297 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.