ESP-Claw is an AI agent framework that runs on Espressif IoT chips and lets people define device behavior through conversation. It handles local sensing, decision-making, and execution for connected devices, with support for event-driven actions, structured memory, and MCP communication.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add espressif/esp-claw --skill blegit clone --depth 1 https://github.com/espressif/esp-clawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/espressif/esp-claw/ble)<a href="https://agentmods.dev/skills/espressif/esp-claw/ble"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/ble/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/espressif/esp-claw/ble"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/ble.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.03839 |
| Opus 5.5 | $0.00010 | $0.01536 |
| Sonnet 5.5 | $0.00005 | $0.00768 |
| Haiku 4.5 | $0.00002 | $0.00384 |
Grade A, and why
ble scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BLE Skill (lua_module_ble · Phase 1C)
This skill describes how an Agent can control the BLE module on ESP-Claw via Lua scripts. The module is a thin ESP-IDF NimBLE adapter; it does not depend on LuatOS, Arduino, or any intermediate framework.
Capabilities (Phase 1C)
- BLE controller and NimBLE host bring-up / teardown
- Legacy (BT4) connectable advertising with device name, appearance, and 16-bit service UUIDs
- Fixed 3-slot connection table with stable
conn_indexidentifiers - MTU preference and per-connection MTU tracking
- Unified event queue:
ble.on_event(fn)+ble.process_events(timeout_ms) - Peripheral-side disconnect (
ble.disconnect) - Module diagnostics via
ble.stats() - Dynamic GATT Server via
ble.gatts_define(profile) - Cached characteristic values via
ble.gatts_set_value()andble.stats({ char = ... }) - Server-initiated
ble.notify()/ble.indicate()using stableconn_index - SMP configuration via
ble.smp_config(opts)beforeble.init()
Not in Phase 1: Central / scanning / GATT Client, passkey / numeric comparison Lua callbacks, bond-management Lua APIs, BLE 5.x extended advertising.
Mutual Exclusion with lua_module_ble_hid
Skill selection hard rule
When the user asks only for "broadcasting", "advertising", "normal BLE",
"BLE", "GATT", service discovery, characteristic read/write, notify, or
indicate, use only this ble skill. Do not use ble_hid as a fallback for
ordinary BLE advertising or GATT tasks.
Use ble_hid only when the user explicitly mentions HID, keyboard, mouse,
media controls, consumer control, typing text, key combos, cursor movement,
clicking, or scrolling.
Hard rule: lua_module_ble and lua_module_ble_hid must never advertise
simultaneously. Both modules share the single BLE controller and NimBLE host;
running both at the same time causes undefined behaviour.
Switching from BLE → HID:
- Call
ble.adv_stop()thenble.deinit(). - Start
lua_module_ble_hid(e.g. viaskills/ble_hid/scripts/start_ble_hid.lua). - Inform the user that the mode has changed.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · -1 lines 15351cf9642c
- 1mo ago First seen · 426 lines · 24 tokens per session scan A 79ec38633972
ble is a skill published in the GitHub repository espressif/esp-claw (2,260 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 3,839 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.