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 LogicLabsAI/ultramemory-mcp --skill swarmgit clone --depth 1 https://github.com/LogicLabsAI/ultramemory-mcpWrote 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/logiclabsai/ultramemory-mcp/swarm)<a href="https://agentmods.dev/skills/logiclabsai/ultramemory-mcp/swarm"><img src="https://agentmods.dev/badge/skills/logiclabsai/ultramemory-mcp/swarm/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/logiclabsai/ultramemory-mcp/swarm"><img src="https://agentmods.dev/badge/skills/logiclabsai/ultramemory-mcp/swarm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00090 | $0.00744 |
| Opus 5 | $0.00045 | $0.00372 |
| Sonnet 5 | $0.00018 | $0.00149 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
swarm 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 10d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarm — Parallel Sub-Agent Fan-Out
Why this exists
Under load, agents drift back to serial execution — reading one file, then another, then another — even when the questions are independent. Serial reads waste wall-clock and the human's attention. This skill is the durable fix: when the pattern matches, fan out.
When to invoke (all three true)
- 2+ independent questions — each answerable without another's result.
- Read-only or non-conflicting — no shared file writes, no single-writer state (a git commit, a service restart, one config file two agents would both edit).
- Bounded synthesis — you can hold the union of N short reports in context.
Trigger patterns: multi-source research (web + repo + package registry + docs) → one agent per source; multi-target verification (logs + config + git + db state) → one agent per target; 3+ independent file reads → one agent per file (or grouped); a verifier cluster after a fix → fan out across measurement angles.
When NOT to
Sequential dependencies (each step needs the prior result); shared writes (race conditions); single-writer operations (restart, commit); trivial single-tool work (overhead exceeds benefit).
How
Use the Agent tool with several calls in one message so they run in parallel:
Agent({ description: "...", subagent_type: "general-purpose", prompt: "<self-contained brief>" })
Agent({ description: "...", subagent_type: "general-purpose", prompt: "<self-contained brief>" })
Agent({ description: "...", subagent_type: "general-purpose", prompt: "<self-contained brief>" })
For long investigations, pass run_in_background: true and collect results as they land.
Briefing rules (each worker starts with ZERO context)
Every brief must be self-contained: (1) context — the system + why it matters (1–3 sentences); (2) question — exactly one (or 2–3 tightly related); (3) tools/methods — where to look, exact commands; (4) constraints — read-only, cap the report; (5) output structure — numbered sections; (6) success criteria. Keep each brief under ~300 words and each worker report under ~500 words — concision keeps synthesis tractable.
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.
- 10d ago First seen · 63 lines · 90 tokens per session scan A cfa37b71e6f8
swarm is a skill published in the GitHub repository LogicLabsAI/ultramemory-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 744 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
dashboard
Open OwnMem Console, the local dashboard for this repository's memory. Use when the user asks to open the dashboard, see memory metrics, check adoption or recall quality, or set up the optional embedding lane. Requires a repository initialized with the dashboard layer.
recall
Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
memory-write
Captures a durable fact to project memory through the kit's safe write path (PoisonGuard secret/injection screening + home-path sanitization + dedup + conflict detection) — preferring the cmk MCP tools (mkremember / mkforget / mktrust) when connected, falling back to the cmk CLI. Use when the user says "remember…
bootstrap
Scaffolds the core-memory-kit directory structure (context/, scripts/, cron/jobs/) into the current project. Idempotent — never overwrites existing files. Run once per project after installing the plugin. Use when the user says "bootstrap the memory system", "set up memory here", or "scaffold the memory kit".
brain-compiler
Generate or refresh SAN using the canonical contract and Agent Brain tools.