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 instructions/aiyo28/memento-os/agents-mdgit 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/instructions/aiyo28/memento-os/agents-md)<a href="https://agentmods.dev/instructions/aiyo28/memento-os/agents-md"><img src="https://agentmods.dev/badge/instructions/aiyo28/memento-os/agents-md.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 | $0.00762 | $0.00762 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
memento-os AGENTS.md 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — Memento OS
What This Repo Is
A Claude Code plugin for persistent AI memory. Core unit: reasoning artifacts ([D], [I], [E], [S]) with invalidation/activation triggers.
If You're Working On This Repo
- Skills are in
skills/*/SKILL.md— each namespaced asmemento:* - Commands are in
commands/memento/*.md - Hooks are in
hooks/hooks.json(prompt-type hooks for Stop and PreCompact) - Plugin manifest is
.claude-plugin/plugin.json(v2.0.0) - Adapters for non-Claude-Code tools are in
adapters/— each subdirectory maps to one AI tool - Starter vault templates are in
starter/obsidian-vault/— these define the vault structure users get
Conventions
- Artifact format:
[D] conclusion — invalidates if trigger [priority] [date] - Seed format:
[S] idea — activates when condition [priority] [date] - Priority: confidence x impact → critical/volatile/settled/noise
- Cap: 24 artifacts per project (Kobe rule). Evict noise first.
- Skills produce artifacts as byproduct — grill-me surfaces
[D]/[I], decide captures[D]or plants[S]
Retrieval-First Protocol
Skills that make decisions MUST search the vault before acting:
memento:decide→ search for prior[D]artifacts before presenting optionsmemento:grill-me→ load domain-relevant vault notes as context- Future decision-making skills → follow the same pattern
The vault is a retrieval source, not just a write destination. Search first, then fill gaps.
Confidence Gate
Before any implementation decision: self-assess "Do I have full context?" If < 96% → pause and retrieve before acting.
Protected domains (always retrieve, regardless of confidence):
- Authentication / authorization patterns
- Database schema / migration decisions
- API contract decisions
- Deployment / infrastructure choices
- Pricing tiers / subscription logic
- Tag architecture / taxonomy
Retrieval sequence:
_context.mdActive Reasoning Artifacts table —[D]entries matching domainDecisions/*{topic}*— full artifact files- If found → surface: "Existing decision:
[D] {statement}— {date}". Ask: reaffirm, revise, or override? - If not found → fresh analysis
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 · 70 lines · 762 tokens per session scan A 91b938547073
memento-os AGENTS.md is an instructions file published in the GitHub repository Aiyo28/memento-os (3 stars, last pushed 2mo ago), licensed MIT. It adds 762 tokens to every session, about $0.0038 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 instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.