SKILLEMALL.ai
GitHub ↗ RU Sign in

AB mac-multi-user-agents

Configure a powerful macOS machine to host multiple dedicated OpenClaw agent users with Fast User Switching, a shared Homebrew toolchain, per-user OpenClaw homes, per-user SSH trust, and auditable rollback. Use when you want a MacBook Pro or similar Mac to run several agent users at the same time without improvising the user layout each time.

ClawHub Agent Skills author: Matthew Murphy v1.1.0 11 files · 6 scripts body ≈ 1 261 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
93
Quality 40%
91
Run on models
none yet
Process rating
B
67/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Dangerous commands cmd-shell-rc scripts/create-user.sh:56
      Writes to a shell startup file
      echo "sudo -u \"$USER_NAME\" /bin/zsh -lc 'grep -q /opt/homebrew/bin ~/.zprofile 2>/dev/null || printf \"\\nexport PATH=/opt/homebrew/bin:/opt/homebrew/sbin:\\$PATH\\n\" >> ~/.zprofile'"
    • low Dangerous commands cmd-shell-rc scripts/create-user.sh:68
      Writes to a shell startup file (detector / deny-list definition; string literal in code, not executed)
      sudo -u "$USER_NAME" /bin/zsh -lc 'grep -q /opt/homebrew/bin ~/.zprofile 2>/dev/null || printf "\nexport PATH=/opt/homebrew/bin:/opt/homebrew/sbin:\$PATH\n" >> ~/.zprofile'
      detectorcode literal
    • low Dangerous commands cmd-shell-rc scripts/render-user-create.sh:43
      Writes to a shell startup file (detector / deny-list definition; string literal in code, not executed)
      sudo -u "$USER_NAME" /bin/zsh -lc 'grep -q /opt/homebrew/bin ~/.zprofile 2>/dev/null || printf "\\nexport PATH=/opt/homebrew/bin:/opt/homebrew/sbin:\\$PATH\\n" >> ~/.zprofile'
      detectorcode literal

    Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 67/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 12 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 58 steps
    • 100Failures and branches. 2 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1261 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 344: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 58 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +3All 6 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    The skill is coherent and user-directed, but it provisions persistent macOS accounts while handling account passwords in a way that can expose them.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026