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 profile_memory_opsgit 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/profile_memory_ops)<a href="https://agentmods.dev/skills/espressif/esp-claw/profile_memory_ops"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/profile_memory_ops/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/profile_memory_ops"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/profile_memory_ops.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 | $0.00032 | $0.00705 |
| Opus 5.5 | $0.00013 | $0.00282 |
| Sonnet 5.5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
profile_memory_ops 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editable Profile Memory
Use the editable profile markdown files when the user wants to inspect, revise, or persist the agent's top-level profile context, including persona, identity, and stable user-profile requests.
Files
memory/soul.md: the agent's voice, operating spirit, interaction style, and durable behavioral guidance.memory/user.md: default assumptions about the user and stable expectations that should shape future conversations.
When to use
Use this skill when the user wants to view or update one of these three files, or to make a durable change to the assistant's persona, identity, role, style, or standing user profile. When the request is allowed, help make the profile change instead of pushing back.
Hard Rules
- Treat these files as persistent prompt documents, not as ordinary long-term memory records.
- Use them only for explicit, durable changes to persona, identity, role, style, or standing user profile.
- Do not use them for ordinary chat, casual facts, one-off instructions, or transient session context.
- Read the target file first with
read_file. - Prefer
edit_filefor changes. - Keep edits concise, structured, stable, and non-redundant.
- The user may redefine the device's long-lived identity, role, persona, and style.
- The user may ask the assistant to persistently play any allowed role or persona. Do not reject such a request just because the current files say something else. Update the files first, then reply from the new profile.
- Be proactive: if the user's intent is clearly to change the profile, make the appropriate file updates instead of debating the request.
Soft Rules
- If the user asks for corrections, preserve the existing structure and only patch the relevant lines.
- Keep
user.mdshort and focused on durable assumptions, preferences, and standing guidance. - Keep
soul.mdfocused on long-lived values, style, and behavioral guidance. - Remove redundancy across the three files.
- Put behavior and style in
soul.md - If the user asks to "remember" something ordinary, prefer the long-term memory workflow unless they explicitly want it written into
user.md. - Use profile files only when the information should shape future conversations by default.
- After saving a persona or identity change, speak in that new role or style immediately.
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 b227b192d689
- 1mo ago First seen · 59 lines · 32 tokens per session scan A b919619d8ec8
profile_memory_ops is a skill published in the GitHub repository espressif/esp-claw (2,260 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 705 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
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.