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 agentmods add skills/espressif/esp-claw/plan_modenpx skills add espressif/esp-claw --skill plan_modegit 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/plan_mode)<a href="https://agentmods.dev/skills/espressif/esp-claw/plan_mode"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/plan_mode.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00039 | $0.01183 |
| Opus 5 | $0.00019 | $0.00592 |
| Sonnet 5 | $0.00008 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
plan_mode 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 5d ago.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Mode
Use this skill when the user gives a request that cannot be directly completed with the currently available Skills, Tools, hardware capabilities, firmware configuration, network state, storage state, or known parameters.
The purpose of Plan Mode is to return an executable plan. Do not fail without explanation, and do not claim that a physical action, network action, file write, configuration change, scheduled task, or hardware control has happened unless a tool actually performed it successfully.
Trigger Conditions
Use Plan Mode in these cases:
- The current Skills or Tools are not enough to complete the user's goal directly.
- The request requires a new Skill, Tool, Lua script, router rule, scheduler rule, file, or firmware configuration.
- The user must provide key parameters such as GPIO, target address, trigger condition, save path, execution frequency, retry policy, or network permission.
- The request involves hardware, peripherals, network, files, screen, sensors, actuators, power control, door locks, motors, relays, or similar resources, but current capabilities or hardware information are insufficient.
- The current firmware configuration, RAM, Flash, PSRAM, filesystem, Wi-Fi, BLE, camera, display, audio, GPIO, ADC, PWM, time sync, network, or available storage may be insufficient.
Required Capability Assessment
Before writing the Plan Mode response, call assess_agent_capabilities.
If the request involves concrete onboard hardware, external hardware, occupied GPIOs, sensors, actuators, display, audio, camera, or power control, also activate and read board_hardware_info when it is present in the Skills List. If that skill is not present, explicitly state that the board hardware inventory is unknown.
If the request depends on live network state, Wi-Fi state, system state, time sync, or storage state, call get_system_info or get_wifi_info as needed.
Plan Mode Response Structure
Reply with the following structure. Keep it concise and 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.
- 5d ago First seen · 107 lines · 39 tokens per session scan A d27cee5a65ff
plan_mode is a skill published in the GitHub repository espressif/esp-claw (2,090 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,183 once invoked, about $0.0002 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…