Mesh API

What it does

When your agent uses it

• Tasks that involve Fine-tuning
• Tasks that involve LLM inference and serving

Example prompts

• “/mesh-api”

Requirements

• A credential in MESH_API_KEY

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Character limit. Meshtastic mesh messages have a strict practical limit. Keep any message you send via POST /send under 200 characters…
2. 2No unsolicited long messages. Never send AI-generated text directly to the mesh without user confirmation if the text exceeds one chunk…
3. 3Bot-loop prevention. Messages prefixed with m@i- are AI-generated mesh messages. If you see this prefix on an inbound mesh message (via…
4. 4Node ID format. Meshtastic node IDs are hex strings matching the pattern ! followed by exactly 8 hexadecimal characters (e.g. !a1b2c3d4)…
5. 5Connection check. Before sending messages, it is good practice to call GET /connection_status to verify the mesh radio is connected. If…
6. 6No auth by default. MESH-API does not require authentication in its default configuration. The MESH_API_KEY env var is optional…
7. 7Rate awareness. Meshtastic is a low-bandwidth LoRa network. Do not send rapid bursts of messages. If you need to send multiple messages…

What it can do on your machine

Read from SKILL.md and the folder at commit ea3cf12. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • MESH_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mesh API loads about 1.8k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 825 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~35

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mr-tbot/mesh-api at commit ea3cf12, republished under its GPL-3.0 licence (© mr-tbot). 825 words, ~1,837 tokens.

name

mesh-api

description

Interact with a Meshtastic LoRa mesh network through MESH-API — list nodes, read messages, send texts, and check connection status.

version

1.0.0

author

mesh-api community

curl -s "$MESH_API_URL/nodes"

[
  {"id": "!a1b2c3d4", "shortName": "TBot", "longName": "TBot Base Station"},
  {"id": "!e5f6a7b8", "shortName": "Hike", "longName": "Hiker Node"}
]

curl -s "$MESH_API_URL/messages"

curl -s -X POST "$MESH_API_URL/send" \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello from OpenClaw", "node_id": "!a1b2c3d4", "direct": true}'

curl -s -X POST "$MESH_API_URL/send" \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello mesh!", "channel_index": 0}'

{"status": "sent", "to": "!a1b2c3d4", "direct": true, "message": "Hello from OpenClaw"}

curl -s -X POST "$MESH_API_URL/ui_send" \
  -d "message=Hello+mesh!&channel_index=0"

curl -s "$MESH_API_URL/connection_status"

{"status": "connected", "error": null}

curl -s "$MESH_API_URL/commands_info"

[
  {"command": "/ping", "description": "Check if the bot is online"},
  {"command": "/ai-9z", "description": "Ask the AI a question"},
  {"command": "/nodes", "description": "List online mesh nodes"}
]

© mr-tbot, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in openclaw-release/skills/mesh-api of mr-tbot/mesh-api.

Open the folder on GitHubat commit ea3cf12