decide

decide is a command for Claude Code from vmarcondes-nilo/personal-os. It costs 0 tokens per session (637 once invoked), scanned A, original, MIT.

A command for working through an important decision and saving the result as a decision record. It asks about context, options, trade-offs, and how easily each option can be undone.

In plain words
What is it for?
Evaluating personal or work decisions and recording the chosen direction.
Why use it?
It turns an uncertain choice into a documented comparison aligned with current goals.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/vmarcondes-nilo/personal-os/decide
Clone the repo
git clone --depth 1 https://github.com/vmarcondes-nilo/personal-os

Made for: Claude Code.

Wrote 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.

agentmods badge for decide

README.md
[![agentmods](https://agentmods.dev/badge/commands/vmarcondes-nilo/personal-os/decide.svg)](https://agentmods.dev/commands/vmarcondes-nilo/personal-os/decide)
Your own site
<a href="https://agentmods.dev/commands/vmarcondes-nilo/personal-os/decide"><img src="https://agentmods.dev/badge/commands/vmarcondes-nilo/personal-os/decide.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00637
Opus 5 $0.00000 $0.00318
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00064

Measured 5d ago against content hash 9af41b5295cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

decide 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.

.claude/commands/decide.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Logger

Help think through and log an important decision. This is a structured coaching conversation that ends with a saved decision record.

Topic: $ARGUMENTS


1. Read Context

Read these files for background:

  • decisions/_template.md — output format
  • Current quarter's OKR file in goals/ — decisions should align with goals
  • Relevant area file in areas/
  • Recent entries in decisions/ — to see past decisions and avoid revisiting settled ones

2. Clarify the Decision

If $ARGUMENTS is provided, use it as the starting point. Otherwise ask: "What decision are you wrestling with?"

Then clarify:

  • "What's forcing this decision now?" — understand the trigger and urgency
  • "What happens if you do nothing?" — check if it even needs deciding today
  • Area: Which life area does this touch?

Keep this tight — 2-3 questions max. Don't over-interview.

3. Map Options

Ask: "What options are you considering?"

Let the user go first, then:

  • Add options they might be missing (there's almost never just 2)
  • For each option, briefly note:
    • Upside: best realistic outcome
    • Downside: worst realistic outcome
    • Reversibility: easy to undo, or a one-way door?

4. Pressure-Test

Pick the right lens for this decision:

Strategic decisions (company, product, hiring):

  • Pre-mortem: "It's 6 months later and this failed — what went wrong?"
  • First principles: "What assumptions are baked in here?"

Resource decisions (time, money, priorities):

  • "What are you saying no to by saying yes to this?"
  • 80/20: "Which option gets 80% of the result with 20% of the effort?"

Personal decisions (family, health, lifestyle):

  • "What will you regret NOT doing?"
  • "What aligns with your values?" (reference profile/values.md)
  • "What would you tell a friend in this situation?"

Be direct. Challenge weak reasoning. Don't just validate — push back.

5. Decide

Push for a clear outcome:

  • "What are you going to do?"
  • "By when?"
  • "Who needs to know?"
  • "What's the first concrete action?"

Read the full file on GitHub · 78 lines

Changes

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.

  1. 5d ago First seen · 78 lines · 0 tokens per session scan A 9af41b5295cb

Subscribe to this mod's changes

decide is a command published in the GitHub repository vmarcondes-nilo/personal-os (43 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 637 tokens. 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.