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 terrizoaguimor/celiums-memory --skill surface-learningsgit clone --depth 1 https://github.com/terrizoaguimor/celiums-memoryWrote 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/terrizoaguimor/celiums-memory/surface-learnings)<a href="https://agentmods.dev/skills/terrizoaguimor/celiums-memory/surface-learnings"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/surface-learnings/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/terrizoaguimor/celiums-memory/surface-learnings"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/surface-learnings.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 | $0.00060 | $0.00983 |
| Opus 5 | $0.00030 | $0.00491 |
| Sonnet 5 | $0.00012 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
surface-learnings 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 9d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Reflex: Surface Learnings
Neural Basis
When asked "what do you know about X", the brain doesn't replay every episodic memory linearly. The hippocampus and prefrontal cortex collaborate to synthesize patterns — recurring themes, stable preferences, emotional baselines — and present a digest, not a transcript.
This skill mirrors that synthesis. It surfaces what the system has learned, not what it has stored.
Squire & Wixted (2011). The cognitive neuroscience of human memory since H.M. Annual Review of Neuroscience, 34, 259-288. Tulving (1985). Memory and consciousness. Canadian Psychology, 26(1), 1-12.
When It Fires
Trigger phrases (any of these → fire immediately):
- "what have you learned"
- "what do you know about me"
- "show me memory stats"
- "memory state"
- "what patterns do you see"
- "show me what you remember"
- "/reflexes"
- "/learnings"
- "/memory"
Also fires when the user asks for a status check after a long session.
The Instinct
Do NOT dump every memory. Synthesize patterns. Three calls, one digest.
1. timeline(hours: 168, limit: 30) — recent week of activity
2. recall(query: "decision preference identity", limit: 10) — high-signal items
3. emotion() — current PAD baseline
Then synthesize into a structured digest with these sections:
1. Identity & Preferences
The 3-5 most stable facts about the user (name, role, location, working style). Pull from memories tagged "identity" or with high importance + repetition.
2. Decisions Made
The 3-5 most recent or important decisions, with their reasoning. Filter to memories that contain "DECISION:", "decided to", "chose".
3. Open Threads
What is unresolved. Pull from session-handoff memories with "OPEN:" content.
4. Current State
- Feeling label from
emotion()("content", "stressed", "energized", etc.) - PAD vector in one line:
P:0.4 A:0.2 D:0.6 - Brief interpretation: "Calm and focused" / "Tense, may need a break"
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.
- 9d ago First seen · 116 lines · 60 tokens per session scan A c31e4ca8a906
surface-learnings is a skill published in the GitHub repository terrizoaguimor/celiums-memory (23 stars, last pushed 17d ago), licensed Apache-2.0. It adds 60 tokens to every session and 983 once invoked, about $0.0003 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
openmemory
Manage persistent memory via OpenMemory MCP. TRIGGER when: user says "remember this", "save to memory", "store this", "recall", "what do you remember about", "check memory", "forget this", "delete memory", "clean up memory", or when agent forms a stable conclusion worth persisting. DO NOT TRIGGER when: user refers to…
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
mode-creator
Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
knowledge-agent
Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.
claude-mem-install
Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.