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 cap_llm_inspect_imagegit 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/cap_llm_inspect_image)<a href="https://agentmods.dev/skills/espressif/esp-claw/cap_llm_inspect_image"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/cap_llm_inspect_image.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00376 |
| Opus 5 | $0.00009 | $0.00188 |
| Sonnet 5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
cap_llm_inspect_image 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 8d 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.
What it actually says
Image Inspection
Use this skill when the user wants the device to inspect a local image and describe what is visible.
When to use
- The user asks what is in an image, photo, screenshot, or camera frame.
- The image already exists on the device filesystem.
- The task needs visual analysis rather than plain file reading.
Available capability
inspect_image: analyze one local image from an absolute path using a prompt that says what to inspect.
Calling rules
- Call
inspect_imagedirectly. - Always pass an absolute local file path in
path. - Always pass a clear
promptthat tells the model what to look for. - Confirm or discover the image path first if it is not already known.
- Do not pass remote URLs or non-image files.
Path guidance
- Prefer real local paths already stored on the device.
- If the exact path is unknown, inspect storage first with file capabilities such as
list_dir. - Common roots in this demo include
<storage_root>/inbox,<storage_root>, or other application-managed storage paths.
Example
{
"path": "<storage_root>/inbox/photo.jpg",
"prompt": "Describe the main objects in this image and mention any visible text."
}
Notes
- Keep the prompt specific. For example: identify objects, read visible text, describe a scene, or check whether a target item appears.
- If the image is blurry or uncertain, report that uncertainty instead of over-claiming.
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.
- 8d ago First seen · 49 lines · 17 tokens per session scan A 1a768470cffb
cap_llm_inspect_image is a skill published in the GitHub repository espressif/esp-claw (2,096 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 376 once invoked, about $0.0001 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.