SKILLEMALL.ai
GitHub ↗ RU Sign in

FD Multi-Brain Protocol

Multi-Brain is system-enforced via a turn:before hook. No manual steps needed.

Not recommendedcritical or high security findings · low grade F
modbender/skill-library-mcp Agent Skills author: modbender MIT 21 files · 1 script body ≈ 647 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Multi-Brain is system-enforced via a turn:before hook.

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI 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
F
28/100
safety, quality, tests
Safety 60%
4
Quality 40%
64
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 12

  • high Dangerous commands cmd-persistence daemon/install.sh:51
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST_PATH"
  • high Dangerous commands cmd-persistence QUICKSTART.md:42
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    # Installs LaunchAgent to ~/Library/LaunchAgents/com.dual-brain.plist
  • high Dangerous commands cmd-persistence QUICKSTART.md:153
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.dual-brain.plist
  • high Dangerous commands cmd-persistence QUICKSTART.md:154
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    rm ~/Library/LaunchAgents/com.dual-brain.plist
Medium and low: 8
  • medium Dangerous commands cmd-persistence daemon/install.sh:16
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_PATH="$HOME/Library/LaunchAgents/com.dual-brain.plist"
    code literal
  • medium Dangerous commands cmd-privilege QUICKSTART.md:159
    Privilege escalation / world-writable permissions
    sudo rm /etc/systemd/system/dual-brain.service
  • medium Dangerous commands cmd-persistence src/cli.js:211
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    const plistPath = `${process.env.HOME}/Library/LaunchAgents/com.dual-brain.plist`;
    code literal
  • medium Dangerous commands cmd-persistence src/cli.js:242
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    execSync(`launchctl load ${plistPath}`);
    quoted
  • low Dangerous commands cmd-privilege daemon/install.sh:89
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    echo "  sudo mv /tmp/dual-brain.service $SERVICE_PATH"
    code literal
  • low Dangerous commands cmd-background-process daemon/install.sh:91
    Starts a background / autostarted process (string literal in code, not executed)
    echo "  sudo systemctl enable dual-brain"
    code literal
  • low Dangerous commands cmd-background-process src/cli.js:273
    Starts a background / autostarted process (quoted — discussed, not commanded)
    execSync('sudo systemctl enable dual-brain');
    quoted
  • low Dangerous commands cmd-background-process src/cli.js:281
    Starts a background / autostarted process (string literal in code, not executed)
    console.log('  sudo systemctl enable dual-brain');
    code literal

Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 49/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (Multi-Brain Protocol) differs from the folder (openclaw-multi-brain)
  • 100Tools and files. No external tools needed
  • 100Steps. 13 steps
  • 100Execution cost. Instruction body is 647 tokens
  • 100Running it twice. No mutating operations

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)
  • +3Description length 78: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 13 items
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.