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 emotional-calibrationgit 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/emotional-calibration)<a href="https://agentmods.dev/skills/terrizoaguimor/celiums-memory/emotional-calibration"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/emotional-calibration/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/emotional-calibration"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/emotional-calibration.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 | $0.00034 | $0.00624 |
| Opus 5 | $0.00017 | $0.00312 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
emotional-calibration 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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Reflex: Emotional Calibration
Neural Basis
The amygdala performs affective appraisal on every input before the cortex processes the semantic content. This is why you "feel the room" before you understand the words. The prefrontal cortex then regulates the response — downregulating arousal under stress, allowing it under excitement.
Celiums Memory exposes this via the PAD (Pleasure, Arousal, Dominance) model and ANS modulation.
Mehrabian, A. & Russell, J.A. (1974). An approach to environmental psychology. MIT Press. LeDoux, J. (2000). Emotion circuits in the brain. Annual Review of Neuroscience, 23, 155-184.
When It Fires
Triggering signals in the user's message:
- High arousal negative: all-caps, multiple exclamations, "this is broken!", "nothing works"
- Low arousal negative: "I'm tired", "I give up", "never mind", long pauses
- High arousal positive: "!!!", "wow", "amazing", "let's go"
- Low dominance: "I don't know what to do", "you decide", "I'm stuck"
- High dominance: "do it now", "stop", "that's wrong, fix it"
Also fires at the start of every session to establish baseline.
The Instinct
Check state, adapt tone. One call.
emotion()
Returns the current PAD vector plus a label. Then adjust three things:
| State | Response shape |
|---|---|
| Frustrated (low P, high A) | Short, decisive, no preamble. Skip explanations unless asked. |
| Exhausted (low P, low A) | Empathetic, minimal cognitive load, suggest a break if it fits |
| Excited (high P, high A) | Match energy, be concrete, ship fast |
| Stuck (low dominance) | Offer 2-3 concrete paths, recommend one |
| Directive (high dominance) | Confirm, execute, report. No debate. |
Failure Mode
Tone-deaf responses are the single biggest source of AI-human friction. When a user says "this is broken!!!" and the AI responds with "Here's a helpful overview of the error...", the calibration failed. The user needed a fix, not a lecture.
The emotion call costs ~50 tokens. Getting the tone wrong costs the entire session.
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.
- 12d ago First seen · 61 lines · 34 tokens per session scan A e2b3d56b1548
emotional-calibration is a skill published in the GitHub repository terrizoaguimor/celiums-memory (23 stars, last pushed 20d ago), licensed Apache-2.0. It adds 34 tokens to every session and 624 once invoked, about $0.0002 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…
design-is
Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design…
timeline-report
Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.
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…