memento:decide SKILL.md skillA

memento:decide from aiyo28/memento-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add aiyo28/memento-os/memento:decide@v2.0.0

Pins v2.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
aiyo28/memento-os
Path
skills/decide/SKILL.md
Versions recorded
2
Latest version
v2.0.0, committed Apr 11, 2026
First version recorded
Mar 21, 2026
Size
4,760 bytes
Repository stars
4
License
MIT

Composable decision skill. Core OODA loop: present options, assess confidence, record reasoning artifact with priority matrix. Modes: default (decide from current context), --research (ingest source first, then decide), --reframe (force perspective shift before options). Triggers: "decide", "should we", "which option", "evaluate", "compare", "research this" (with decision intent), "let's think about".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# /decide

One skill. Three modes. Every decision produces a reasoning artifact with a priority level.

## Setup

The vault path is configured during `memento init`. If not set, ask the user where their vault lives.

## Mode Detection

| Signal | Mode | What happens |
|--------|------|-------------|
| Decision needed from current context | `default` | Jump to OODA loop |
| URL, file, or "research this" provided | `--research` | Ingest source → extract → then OODA loop |
| "reframe", "different angle", "what am I missing" | `--reframe` | Force perspective shift → then OODA loop |

## Mode: --research (Ingest First)

Extract knowledge from the source before deciding.

### Extraction Engine (5 Fields)

1. **Core argument** — what it argues, not what it's about (1-2 sentences)
2. **Why it holds** — evidence, reasoning, mechanism (3 bullets max)
3. **Technical specifics** — numbers, code patterns, tools. "None" if none
4. **Execution pattern** — the craft move worth stealing. Omit if N/A
5. **Open questions** — what connects to existing work? What assumption might break?

After extraction, ask: "Does this inform a decision, or is it reference material?"
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add aiyo28/memento-os/memento:decide@sha256:ff7784c35c86fa84

The line at the top of this page pins the label v2.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_abo74vfuumzdqfad.svg)](https://markdownregistry.com/a/art_abo74vfuumzdqfad)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Mar 21, 2026 and Apr 11, 2026, about one every 21 days.

versioncommittedcommitsizeaudit
v2.0.0 latest2026-04-11 a501408 4,760 BA view · diff
v2.0.02026-03-21 5b7f6d1 4,207 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4760 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

aiyo28/memento-os · 4 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_abo74vfuumzdqfad
GET https://markdownregistry.com/api/v1/resolve?ref=aiyo28/memento-os/memento:decide
GET https://markdownregistry.com/api/v1/blob/ff7784c35c86fa84aa45147b8ed05aed6e2862de41a75afc5dfc1921f1337272

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from aiyo28/memento-os

AGENTS.md AGENTS.md file
aiyo28/memento-os · AGENTS.md
git:20260905.601aa1a · audit A · 4 stars
AGENTS.md@adapters/codex AGENTS.md file
aiyo28/memento-os · adapters/codex/AGENTS.md
git:20260520.e0e4c72 · audit A · 4 stars
decide SKILL.md skill
aiyo28/memento-os · adapters/codex/skills/decide/SKILL.md · Composable decision skill. Core OODA loop: present options, assess confidence, record reasoning artifact with priority…
v2.0.0 · audit A · 4 stars
grill-me SKILL.md skill
aiyo28/memento-os · adapters/codex/skills/grill-me/SKILL.md · Stress-test a plan, design, or architecture through relentless structured interviewing. Produces reasoning artifacts as…
v1.1.0 · audit A · 4 stars
decay SKILL.md skill
aiyo28/memento-os · adapters/codex/skills/memento-decay/SKILL.md · Find aged [D] artifacts whose invalidation triggers may have fired. Scans vault _context.md tables, parses the…
v1.0.0 · audit A · 4 stars
lint SKILL.md skill
aiyo28/memento-os · adapters/codex/skills/memento-lint/SKILL.md · Validate every reasoning artifact in vault _context.md tables against schema rules. [D]/[I] need an invalidates clause…
v1.0.0 · audit A · 4 stars
session-complete SKILL.md skill
aiyo28/memento-os · adapters/codex/skills/session-complete/SKILL.md · Run at end of session OR before compaction. Extracts reasoning artifacts with priority matrix, updates NEXT.md, appends…
v4.2.0 · audit A · 4 stars
session-start SKILL.md skill
aiyo28/memento-os · adapters/codex/skills/session-start/SKILL.md · Session opening ritual. Loads context via L0→L1 protocol, displays briefing with active decisions and pending items…
v2.0.1 · audit A · 4 stars
vault-audit SKILL.md skill
aiyo28/memento-os · adapters/codex/skills/vault-audit/SKILL.md · Vault health check. Validates structure, detects stale reasoning artifacts by priority level, processes inbox, and…
v1.1.0 · audit A · 4 stars
llms.txt llms.txt file
aiyo28/memento-os · llms.txt
git:20260905.f7bc340 · audit A · 4 stars
memento:grill-me SKILL.md skill
aiyo28/memento-os · skills/grill-me/SKILL.md · Stress-test a plan, design, or architecture through relentless structured interviewing. Produces reasoning artifacts as…
v1.1.0 · audit A · 4 stars
memento:decay SKILL.md skill
aiyo28/memento-os · skills/memento-decay/SKILL.md · Find aged [D] artifacts whose invalidation triggers may have fired. Scans vault _context.md tables, parses the…
v1.0.0 · audit A · 4 stars

Every file in aiyo28/memento-os

Browse by kind, by grade A, or by owner.