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 decision-encodinggit 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/decision-encoding)<a href="https://agentmods.dev/skills/terrizoaguimor/celiums-memory/decision-encoding"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/decision-encoding.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00525 |
| Opus 5 | $0.00026 | $0.00262 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
decision-encoding 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 7d 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: Decision Encoding
Neural Basis
Declarative memories form through hippocampal encoding at the moment of experience, then consolidate into long-term cortical storage. Decisions are high-salience episodic events — the amygdala tags them with importance, the hippocampus binds the context, and the prefrontal cortex encodes the reasoning.
Eichenbaum, H. (2004). Hippocampus: Cognitive processes and neural representations that underlie declarative memory. Neuron, 44(1), 109-120.
When It Fires
Activation signals:
- "Let's go with X" / "We'll use X" / "Decision: X"
- Choosing between alternatives after evaluation
- Setting a convention, pattern, or rule for the project
- Committing to a deadline, scope, or constraint
- Rejecting an option with stated reasoning (the rejection itself is a decision)
The Instinct
Encode immediately, not later.
remember(
content: "DECISION: <what was chosen> — REASON: <why> — REJECTED: <what and why>",
tags: ["decision", "<domain>"]
)
Three elements are mandatory in the content:
- What — the actual choice
- Why — the reasoning that justified it
- Rejected — alternatives considered and why they lost
Without the "rejected" field, future-you cannot reconstruct the decision tree and will second-guess.
Failure Mode
Decisions lost to context death become zombie patterns: the code still follows them but nobody remembers why, so they get re-debated every session. This is how technical debt accumulates silently.
A decision that is not encoded is a decision that will be re-litigated within 3 sessions.
Example
Bad: remember("Using a database")
Good: remember(
"DECISION: native Rust Hyphae engine behind Cloudflare Containers —
REASON: durable tenant isolation without external storage services —
REJECTED: multi-service external-storage stack",
tags: ["decision", "runtime", "stack"]
)
The good version survives context death. The bad version is noise.
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.
- 7d ago First seen · 61 lines · 52 tokens per session scan A cf0fbc989c6a
decision-encoding is a skill published in the GitHub repository terrizoaguimor/celiums-memory (23 stars, last pushed 15d ago), licensed Apache-2.0. It adds 52 tokens to every session and 525 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.