SKILLEMALL.ai

AC agent-team-mesh

Team-wide P2P mesh for OpenClaw agents running on different containers/pods. Each agent's gateway listens on its own pod IP:18789 over WebSocket; the mesh CLI lets you ping, send-and-await-reply, broadcast, and discover the whole team. No broker, no Supabase, no central server — just direct WS calls between teammates' agents. Includes auto-detect of "this machine's identity" (USER.md / sso.json / env var), secure token storage (separate chmod 600 file, not committed to git), message size limits (4KB warn / 8KB block), --dry-run preview for both send and broadcast, and an optional IM fallback hook when an agent is unreachable. Triggers: "message my teammate's agent", "ping bob's agent", "broadcast to the team", "agent mesh", "team agent communication".

ClawHub Agent Skills author: Evan Song v1.0.0 MIT-0 6 files · 1 script body ≈ 1 677 tokens Open the sourceclawhub.ai analyzed 2 d ago

Team-wide P2P mesh for OpenClaw agents running on different containers/pods.

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

IntegrationSupabaseGitHubAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
97/100
safety, quality, tests
Safety 60%
100
Quality 40%
92
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

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 · 0

    ✓ No critical or high findings

    Files scanned: 6. 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 56/100

    • 0Result and completion. Does not say what the result is
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 4 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 29 steps, 2 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1677 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 12 top-level sections: this looks like several domains in one skill

    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

    • +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
    • +5Description quotes 6 example trigger phrases
    • +3Description length 761: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 29 items
    • +4Has examples (8 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: suspicious
    This is a legitimate team agent messaging tool, but it can forward user messages and relies on shared agent tokens with some under-disclosed fallback behavior.
    LLM: suspicious (high) · VirusTotal: · 20 Jun 2026