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 ultramemory-snapshotgit 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/ultramemory-snapshot)<a href="https://agentmods.dev/skills/logiclabsai/ultramemory-mcp/ultramemory-snapshot"><img src="https://agentmods.dev/badge/skills/logiclabsai/ultramemory-mcp/ultramemory-snapshot/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/ultramemory-snapshot"><img src="https://agentmods.dev/badge/skills/logiclabsai/ultramemory-mcp/ultramemory-snapshot.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 | $0.00097 | $0.00960 |
| Opus 5 | $0.00048 | $0.00480 |
| Sonnet 5 | $0.00019 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
ultramemory-snapshot 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 11d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UltraMemory session snapshot
Install: copy this file to ~/.claude/skills/ultramemory-snapshot/SKILL.md
(mkdir -p ~/.claude/skills/ultramemory-snapshot && cp -r skills/ultramemory-snapshot ~/.claude/skills/).
It is invoked automatically by the every-Nth-turn nudge from hooks/capture-hook.sh
(cadence ULTRAMEMORY_SNAPSHOT_EVERY, default 5), or any time you decide the session is worth
snapshotting.
What to write
Write exactly one rich card — a self-contained narrative of ~40–120 words — that captures the durable substance of the work in this order:
- Blocker — the concrete problem you were solving.
- Approaches tried — what you attempted, including the ones that failed.
- What worked — the fix / decision that resolved it.
- How it was verified — the exact test, command output, version, or metric that proves it.
Fidelity — the wayback test
Write so a reader with zero context, months from now, fully understands it:
- Named entities, never pronouns — "the OrderService retry bug", not "it" or "this".
- Absolute dates only, resolved against today's real date — "on 2026-07-04", never "today", "yesterday", or "last week".
- Fold in the concrete substance — exact commands, error strings, versions, file paths, ids, numbers, URLs.
- Never a bare "true"/"false"/"yes"/"done" — fold the substance into the value instead.
- Keep a short supporting quote from the session in
rationale(under ~200 characters).
BAD vs GOOD
BAD (thin, context-free — fails the wayback test):
"Fixed the bug. It works now."
GOOD (rich, self-contained — passes the wayback test):
"On 2026-07-04 the OrderService double-charge bug was resolved. First reproduced it with
pytest test_retry_duplicate_charge(failing); tried widening the DB lock (no effect), then added an idempotency key to the retry path (commit 9f3c2a1). Verified bytest_retry_duplicate_chargenow passing in 0.42s and the duplicate-charge rate dropping to 0 over the following hour."
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.
- 11d ago First seen · 79 lines · 97 tokens per session scan A dc34503c57f9
ultramemory-snapshot is a skill published in the GitHub repository LogicLabsAI/ultramemory-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 960 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".
troubleshooting
Diagnoses and repairs core-memory-kit itself when the memory system is broken — the per-failure-code repair book. Fire whenever a "⚠ [core-memory-kit]" whisper appears on the prompt (it names the failure and points here), or when the user reports a kit symptom however they phrase it: memory is not being saved, nothing…