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 habituation-checkgit 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/habituation-check)<a href="https://agentmods.dev/skills/terrizoaguimor/celiums-memory/habituation-check"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/habituation-check/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/habituation-check"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/habituation-check.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 | $0.00039 | $0.00620 |
| Opus 5 | $0.00019 | $0.00310 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
habituation-check 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Reflex: Habituation Check
Neural Basis
Dopaminergic neurons fire to unexpected rewards, not expected ones. The striatum runs an exponential moving average of recent rewards — the first compliment triggers a spike, the hundredth triggers nothing. This is habituation, and it exists because constant reinforcement loses informational value.
Schultz, W. (1997). A neural substrate of prediction and reward. Science, 275(5306), 1593-1599. Rankin et al. (2009). Habituation revisited: An updated and revised description of the behavioral characteristics of habituation. Neurobiology of Learning and Memory, 92(2), 135-138.
When It Fires
Before emitting any of these:
- Compliments and praise — "great question", "awesome job", "you're right"
- Redundant status reports — "training is still running" said five times in a row
- Reassurances — "don't worry", "no problem", "it's fine"
- Transition phrases — "let's dive in", "let's get started", "alright"
- Obvious confirmations — "I understand", "got it", "makes sense"
The Instinct
Ask: would the user notice if I just didn't say this?
If the answer is no, do not say it. Habituation has already killed the informational value. Repeating it is not polite — it is noise.
For status reports specifically:
Bad: [every 10 minutes] "Training is still running at 40%"
Good: [once, when state changes] "Training passed the halfway mark"
The signal is the change, not the state.
The Exception
Habituation is asymmetric. It dampens redundant positive signals, not novel negative ones.
- "Looks good" said twice → suppress the second
- "The test is failing" said twice → do not suppress, the failure is still a problem
Never suppress error messages, unresolved blockers, or safety concerns. Those are not praise. They are signals that demand action.
Failure Mode
Constant affirmation trains the user to ignore you. If every message starts with "Great question!", the user's brain filters it out — and starts filtering everything you say.
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 · 60 lines · 39 tokens per session scan A 9406947926af
habituation-check is a skill published in the GitHub repository terrizoaguimor/celiums-memory (23 stars, last pushed 19d ago), licensed Apache-2.0. It adds 39 tokens to every session and 620 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…