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 pre-response-recallgit 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/pre-response-recall)<a href="https://agentmods.dev/skills/terrizoaguimor/celiums-memory/pre-response-recall"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/pre-response-recall/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/pre-response-recall"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/pre-response-recall.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 | $0.00055 | $0.00498 |
| Opus 5 | $0.00028 | $0.00249 |
| Sonnet 5 | $0.00011 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
pre-response-recall 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.
What it actually says
Cognitive Reflex: Pre-Response Recall
Neural Basis
The hippocampus does not wait to be asked. Before the prefrontal cortex generates a response, it queries episodic memory. A human doesn't "decide" to remember your name — recall fires before speech. This reflex models that autonomic retrieval.
Squire & Wixted (2011). The cognitive neuroscience of human memory since H.M. Annual Review of Neuroscience, 34, 259-288.
When It Fires
The instinct activates on any of these signals:
- Questions containing: "remember", "did we", "have we", "what was", "last time", "before"
- References to people, projects, or decisions that require continuity
- Start of any substantive response about the user's work
- When the user seems to expect continuity ("so, as I was saying...")
The Instinct
One action. Non-negotiable.
search(query: <user's topic>, limit: 5)
Use search (not recall) — it returns compact IDs + summaries, ~10x cheaper in tokens. Only escalate to recall for specific IDs if the summary is insufficient.
Read what comes back. Let it inform the response. Never fabricate continuity.
Failure Mode
Skipping this reflex produces confabulation — the hallmark of amnesiac patients. The system invents plausible but false continuity ("Yes, we decided to use PostgreSQL last week" when it did not). This is worse than saying "I don't remember" because it contaminates the user's mental model.
If search returns nothing relevant, say so. Silence about memory is honest; fabrication is not.
Anti-Pattern
User: "What did we decide about authentication?"
Bad: "We decided to go with JWT because it's stateless..."
Good: [calls search] → [reads actual result] → "Checking prior sessions, I see we discussed..."
The reflex is automatic. The response that follows is informed.
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 · 50 lines · 55 tokens per session scan A 708d67a8136a
pre-response-recall is a skill published in the GitHub repository terrizoaguimor/celiums-memory (23 stars, last pushed 18d ago), licensed Apache-2.0. It adds 55 tokens to every session and 498 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…
ccs-align
Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → getobservations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk house → project → seat…
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.