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.
git clone --depth 1 https://github.com/Aiyo28/memento-osWrote 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/rules/aiyo28/memento-os/memento-conventions)<a href="https://agentmods.dev/rules/aiyo28/memento-os/memento-conventions"><img src="https://agentmods.dev/badge/rules/aiyo28/memento-os/memento-conventions/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/rules/aiyo28/memento-os/memento-conventions"><img src="https://agentmods.dev/badge/rules/aiyo28/memento-os/memento-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01035 | $0.01035 |
| Opus 5 | $0.00517 | $0.00517 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
memento-conventions 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 8d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memento OS — Conventions
This project uses Memento OS for persistent AI memory. Store conclusions, not notes. The vault is a retrieval source — search before generating from training data.
Artifact Format
Every piece of memory is a reasoning artifact — a pre-computed conclusion with an expiration condition.
[D] conclusion — invalidates if trigger [priority] [YYYY-MM-DD]
[I] insight — invalidates if condition [priority] [YYYY-MM-DD]
[E] what went wrong — root cause: why [settled] [YYYY-MM-DD]
[S] idea — activates when condition [priority] [YYYY-MM-DD]
| Prefix | Type | Purpose |
|---|---|---|
[D] |
Decision | A choice between alternatives — has an invalidation trigger |
[I] |
Insight | A reusable conclusion — survives the session that produced it |
[E] |
Error | A mistake with root cause + fix — defaults to settled |
[S] |
Seed | A deferred idea — activates when its condition is met, not when time passes |
Optional expiry (for time-bound conclusions only):
[D] conclusion — invalidates if trigger — expires: YYYY-MM-DD [priority] [YYYY-MM-DD]
Do NOT add expiry to foundational architecture decisions.
Priority Matrix
Priority is derived from confidence × impact:
| High Impact | Low Impact | |
|---|---|---|
| High Confidence | critical | settled |
| Medium Confidence | volatile | settled |
| Low Confidence | volatile | noise |
- AI proposes confidence (high / medium / low)
- Ask user: "High or low impact?"
[E]errors default to settled; once resolved → noise- noise priority: ask "store anyway or discard?" — default: discard
Kobe Cap: 24 Artifacts
Maximum 24 artifacts per project in the Active Reasoning Artifacts table.
Eviction order when over cap: noise → settled → volatile → critical (never auto-evict).
Archive evicted artifacts to Decisions/ folder with status: superseded, archived, or active.
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.
- 8d ago First seen · 117 lines · 1,035 tokens per session scan A 7f9330211664
memento-conventions is a cursor rule published in the GitHub repository Aiyo28/memento-os (3 stars, last pushed 3d ago), licensed MIT. It adds 1,035 tokens to every session, about $0.0052 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 2026-08-31.
Other cursor rules, from other repositories
cursor-rules
You have access to a persistent cross-session memory via the memory MCP server. Knowledge survives between sessions and is shared across agents working on the same project.
atomicmemory
AtomicMemory persistent memory protocol and MCP tool usage.
cursor-rules
A rule that automatically records important information from each conversation after it ends.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.