decide

decide is a command for coding agents from brainOS-HQ/brain-os. It costs 0 tokens per session (906 once invoked), scanned A, original, MIT.

A command for recording an already-made strategic decision in Brain OS so it remains part of the project's shared state.

In plain words
What is it for?
It checks for related or contradictory decisions, then logs an approved decision and can update the project's next step or blocker.
Why use it?
It prevents important decisions from being forgotten, accidentally reopened, or recorded in conflict with an existing decision.

Command

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/brainos-hq/brain-os/decide
Clone the repo
git clone --depth 1 https://github.com/brainOS-HQ/brain-os

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/brainos-hq/brain-os/decide.svg)](https://agentmods.dev/commands/brainos-hq/brain-os/decide)
Your own site
<a href="https://agentmods.dev/commands/brainos-hq/brain-os/decide"><img src="https://agentmods.dev/badge/commands/brainos-hq/brain-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 906 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 $0.00000 $0.00906
Opus 5 $0.00000 $0.00453
Sonnet 5 $0.00000 $0.00181
Haiku 4.5 $0.00000 $0.00091

Measured 3d ago against content hash dd799de5d3ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

templates/commands/decide.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brain OS : Decision Capture

Capture a strategic decision so it never gets lost or reopened accidentally.

This is not /strategy (which helps you think a decision through). This captures the decision after it's been made.

REQUIRED FIRST READ

Before any tool call, read ~/.claude/brain-os/PROTOCOL.md. The protocol's "Tool routing" section is load-bearing: decision_check runs BEFORE any write.

Input

Arguments: $ARGUMENTS (format: <entity-name> "<decision summary>"). If no arguments, review what was decided this session and ask what to log.

Primary tool sequence

  1. mcp__brain-os__decision_check(proposed_action, entity_id) : conflict gate, runs FIRST
  2. Gather details (see Step 2 below)
  3. mcp__brain-os__decision_log(...) : persist the decision
  4. mcp__brain-os__entity_update(...) : if the decision changes next_move or clears a blocker

Step 1: Conflict check

decision_check returns one of:

  • clear : no conflict, proceed.
  • caution : a related decision exists. Surface it, ask if this supersedes it.
  • conflict : a contradictory active decision exists. STOP. Show the conflict and ask the user to confirm before proceeding.

Never log a conflict result without explicit user confirmation.

Step 2: Gather details

If a decision summary was provided, confirm and fill in gaps. If not, ask:

  1. What was decided?
  2. Why? (the real reason, not the polite one)
  3. What alternatives were considered, and why rejected?
  4. What's the proof action : one thing that validates this decision?
  5. When should this be reviewed?

One message, not an interrogation.

Step 3: Classify

Assign a decision type:

  • product_direction : what to build, what the product is
  • architecture : how to build it technically
  • scope : what to include or cut
  • priority : what to do first
  • kill_park : stopping or pausing an entity or feature
  • monetization : how to make money
  • brand : identity, voice, positioning

Step 4: Log it

Read the full file on GitHub · 100 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. 3d ago First seen · 100 lines · 0 tokens per session scan A dd799de5d3ea

Subscribe to this mod's changes

decide is a command published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 906 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 2026-08-31.