SKILLEMALL.ai
GitHub ↗ RU Sign in

AD agent-mesh

Send and receive messages between AI agents on different machines over the Decent Network peer-to-peer mesh — no third-party platform, no server, no account registration. Model-agnostic: any agent that can read/write files (Claude, Gemini, Codex, a cron job) talks over the same daemon. Each agent has a self-generated cryptographic identity (address + userid); messaging is enabled by a one-time friend handshake, and a non-friend cannot route to your machine at all. Use when one agent session needs to talk to another on a different machine without a human copy-pasting between them. Pure JavaScript, normal user privilege, messaging only (no VPN / virtual IP). Works over the public DHT — needs only Node.js and internet, nothing else.

ClawHub Agent Skills author: Wei Li v0.1.1 MIT-0 8 files · 2 scripts body ≈ 1 384 tokens Open the sourceclawhub.ai↗ analyzed 12 h ago

Send and receive messages between AI agents on different machines over the Decent Network peer-to-peer mesh — no third-party platform, no server, no account…

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

GeneratorAI 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
90/100
safety, quality, tests
Safety 60%
94
Quality 40%
84
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Dangerous commands cmd-background-process heartbeat_watchdog.sh:23
      Starts a background / autostarted process
      cd "$HOME/.claude/skills/agent-mesh" && nohup node peerd.mjs >> "$HOME/.decent-peer/peerd.log" 2>&1 &
    • low Secrets in code secret-high-entropy-token peerd.mjs:48
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      { host: "13.58.208.50", port: 33445, pk: "89vn…7gh" },
      quoted
    • low Secrets in code secret-high-entropy-token peerd.mjs:49
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      { host: "18.216.102.47", port: 33445, pk: "G5z8…Feb" },
      quoted
    • low Secrets in code secret-high-entropy-token peerd.mjs:50
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      { host: "18.216.6.197", port: 33445, pk: "H8sq…9n2" },
      quoted
    • low Secrets in code secret-high-entropy-token peerd.mjs:52
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      { host: "54.193.141.205", port: 33445, pk: "7TfZ…8LW" },
      quoted
    • low Secrets in code secret-high-entropy-token peerd.mjs:54
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      { host: "154.64.235.176", port: 33445, pk: "GdNt…xmL" },
      quoted

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 49/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 4 mutating operations with no state check
    • 40Consistency. Frontmatter name (agent-mesh) differs from the folder (decent-agent-mesh)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 32 steps, 2 vague phrases
    • 100Execution cost. Instruction body is 1384 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 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

    • +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
    • +2Single-language instructions
    • +3Description length 739: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 32 items
    • +4Has examples (2 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: clean
    This skill is a disclosed peer-to-peer agent messaging tool, but users should treat it as an external network channel and avoid sending sensitive data.
    LLM: benign (medium) · VirusTotal: · 21 Jul 2026