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 agentmods add rules/aiyo28/memento-os/memento-workflowsgit 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-workflows)<a href="https://agentmods.dev/rules/aiyo28/memento-os/memento-workflows"><img src="https://agentmods.dev/badge/rules/aiyo28/memento-os/memento-workflows.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.02218 |
| Opus 5 | $0.00005 | $0.01109 |
| Sonnet 5 | $0.00002 | $0.00444 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
memento-workflows 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 5d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memento OS — Workflows
Trigger these workflows with natural language. Each produces structured output and vault writes.
Session Start Workflow
Triggers: "start session", "what's the context", "where were we", "catch me up"
Step 1 — Load L0 (Session Continuity)
Read NEXT.md in the project root. This is the 15-line continuity doc — Continue, Decide, Blocked sections.
Step 2 — Load L1 (Project Context, ~600 tokens)
Read (skip if missing):
- Project instructions file (
CLAUDE.md,AGENTS.md, or.cursorrules) - Vault
_context.md— top 3 sections only: Summary + Key Numbers + Active Reasoning Artifacts table. STOP before Doc Index / Decision Log / Open Questions / Related sections. This is the L1 partial-read rule. - Peer Card (
People/Self.mdin vault) — Communication Style and Decision Patterns tables only (~20 lines). Skip if missing.
Never auto-load full docs or research files at session start (L2/L3 only on demand).
Step 3 — Seed Activation Check
Scan [S] entries in the Active Reasoning Artifacts table:
- Activation condition appears met → surface under "Seeds Ready" in briefing
- Dormant > 90 days → flag for review
- When a seed activates: "This seed is ready. Want to decide on it?"
Step 4 — Staleness Check
First, check for expired artifacts (past expires: YYYY-MM-DD date) — flag as EXPIRED regardless of priority.
Then priority-based staleness:
| Priority | Age | Status |
|---|---|---|
| critical | > 90 days | STALE — review invalidation trigger |
| volatile | > 30 days | NEEDS RESOLUTION — decide, upgrade, or delete |
| settled | > 90 days | STALE — likely safe to archive |
| noise | Any | Should not be in table — flag for removal |
Step 5 — Display Briefing
## Session Briefing — {Project Name}
Date: {today}
Memory: {score}/10 | {total} artifacts | {seeds} seeds | streak: {n}
### Continue
{from NEXT.md}
### Active Decisions
{critical and volatile only, up to 7}
### Seeds Ready (if any)
{[S] artifacts where activation condition appears met}
### Stale Artifacts (if any)
{list with age and invalidation trigger}
### Pending
{from NEXT.md "Decide" section}
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.
- 5d ago First seen · 213 lines · 9 tokens per session scan A aac45aad9160
memento-workflows is a cursor rule published in the GitHub repository Aiyo28/memento-os (3 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 2,218 once invoked, about $0.0000 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
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.