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/felo-inc/memclaw/memclawnpx skills add Felo-Inc/memclaw --skill memclawgit clone --depth 1 https://github.com/Felo-Inc/memclawWrote 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/felo-inc/memclaw/memclaw)<a href="https://agentmods.dev/skills/felo-inc/memclaw/memclaw"><img src="https://agentmods.dev/badge/skills/felo-inc/memclaw/memclaw.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 | $0.00226 | $0.05361 |
| Opus 5 | $0.00113 | $0.02681 |
| Sonnet 5 | $0.00045 | $0.01072 |
| Haiku 4.5 | $0.00023 | $0.00536 |
Grade A, and why
memclaw 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memclaw — Workspace Manager
The agent's external brain for projects. Once activated, the agent continuously syncs artifacts and knowledge into the corresponding LiveDoc, so that anyone (including future sessions or teammates) can load that workspace and instantly recover full context.
Core Concepts
| Concept | Description |
|---|---|
| Workspace | One project = one LiveDoc |
| Active Workspace | Current session state; all operations auto-sync to this workspace |
| README | The agent's memory of the project; actively maintained by the agent |
| Artifacts | Important outputs; the agent asks before saving |
| Registry | ~/.memclaw/workspaces.json, mapping project names to LiveDoc IDs and project summaries |
Registry format:
{
"workspaces": {
"Health Management": {
"id": "nkYv32xA2dEHNpyT4xdZkq",
"summary": "Triggers when user talks about diet, exercise, weight, calories, health tracking"
}
}
}
Registry maintenance rules:
- After creating a workspace → add a record with
idandsummary - After loading a workspace → if it is not already in the registry, add it
- After deleting a workspace → remove the corresponding record
- After renaming → update the record name
- The
summaryfield syncs from the README summary field. If the API returns a summary, use it; otherwise generate a one-line project description in the user's language. - The registry key must be the project name (in the user's language). Never use a short_id as the key.
- If the API errors (502/401/timeout), do not write or modify the registry. Do not use placeholders or short_id as a fallback. Wait until the API is healthy again before writing.
Project existence verification (important):
- Never decide that a project exists based on memory alone. Before saying "this project already exists", you must verify it via the registry file or
$SCRIPT list --keyword. - short_id must come from a real query result in the current turn (registry, list, or create output), not from stale context in your head.
- If project verification fails (API error), do not pretend the project exists and do not invent project metadata. Tell the user there is a network issue and retry later, or create a new project directly.
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.
- 5d ago First seen · 387 lines · 226 tokens per session scan A e394830a6c3e
memclaw is a skill published in the GitHub repository Felo-Inc/memclaw (40 stars, last pushed 4mo ago), licensed MIT. It adds 226 tokens to every session and 5,361 once invoked, about $0.0011 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
memory-config
Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
memory-recall
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this…
openclaw-plugin
This plugin is a thin adapter between OpenClaw and LycheeMem. It does not replace memory-core, does not claim plugins.slots.memory, and does not duplicate LycheeMem algorithms.
lycheemem
Forceful operating rules for using LycheeMem as the primary structured long-term memory path inside OpenClaw.
memory
Use LycheeMem as Claude Code's structured long-term memory for prior conversations, user preferences, project decisions, timelines, and durable facts.