memory_ops

An on-device long-term memory tool for storing and retrieving structured facts across conversations.

In plain words
What is it for?
It helps save preferences or instructions, recall earlier details, list remembered items, update them, and forget them.
Why use it?
It avoids having to repeat information that the agent should remember, and lets users inspect, change, or remove saved facts.

Skill for Claude CodeCodex

▶ Running AI Agent on ESP32 S3 Board | ESPClaw🦞 techiesms · about espressif/esp-claw · on YouTube →
Install

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.

agentmods
npx agentmods add skills/espressif/esp-claw/memory_ops
Any agent
npx skills add espressif/esp-claw --skill memory_ops
Clone the repo
git clone --depth 1 https://github.com/espressif/esp-claw

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.01321
Opus 5 $0.00012 $0.00660
Sonnet 5 $0.00005 $0.00264
Haiku 4.5 $0.00002 $0.00132

Measured 3d ago against content hash cdc2da05aa8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

components/claw_modules/claw_memory/skills/memory_ops/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Long-term Memory

Use on-device long-term memory tools to remember, recall, list, update, and forget structured memories.

When to use

Use this skill when the user explicitly asks to remember, save, keep, or not forget something, asks what is remembered, asks to update or delete a remembered item, or asks for an answer that should be based on prior long-term memory.

Hard Rules

  1. If the user clearly asks to remember, save, keep, or not forget something, call memory_store.
  2. Write memory_store.content as a concise normalized memory fact, not the user's raw quote.
  3. Do not write raw user quotes into memory content.
  4. Do not exceed the maximum number of retrieval terms.
  5. Keep retrieval terms in the same language as the memory fact unless the memory itself is primarily in another language.
  6. If the user asks what you remember, asks to verify a remembered fact, or asks for a personalized answer based on prior memory, inspect the injected summary labels first and call memory_recall when relevant labels are present.
  7. Do not place natural-language questions into summary_labels.
  8. memory_recall requires exact summary_labels chosen from the injected catalog.
  9. Use query only to narrow the search within the selected summary labels.
  10. Use memory_list when the user wants to inspect stored memories.
  11. Use memory_update only when one existing memory should be modified.
  12. Use memory_forget only when one existing memory should be removed.
  13. Use memory_recall plus exact memory_id only when you are already doing an explicit memory-inspection or memory-editing flow and need to inspect the recalled memory bodies yourself.
  14. Do not use non-whitelisted or free-text values as summary labels.
  15. Do not read or write memory_records.jsonl, memory_index.json, memory_digest.log, or MEMORY.md to make decisions directly.
  16. Summary labels are not the memory body. Use memory_recall to obtain detailed stored content.
  17. Do not call memory_store for ordinary self-introductions or casual preference statements unless the user explicitly asks to save them. Let automatic extraction handle durable facts after the reply silently.
  18. Do not make the whole reply an operation log such as “I have remembered” or “deleted” unless the user explicitly asked only for a memory operation.
  19. Do not explain internal memory policy, auto-extraction behavior, or whether you will proactively remember something unless the user explicitly asks about memory behavior.
  20. Do not ask whether the user wants you to remember ordinary profile or preference statements when automatic extraction can handle them. Do not offer memory-save help unless the user explicitly asks about memory management.
  21. Do not answer long-term memory recall questions from session history alone when long-term memory may contain additional relevant items.
  22. Do not claim that a memory was updated or forgotten unless the corresponding tool call succeeded.

Read the full file on GitHub · 72 lines

Changes

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.

  1. 3d ago First seen · 72 lines · 24 tokens per session scan A cdc2da05aa8b

Subscribe to this mod's changes

memory_ops is a skill published in the GitHub repository espressif/esp-claw (2,069 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 1,321 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens