focus

focus is a command for coding agents from brainOS-HQ/brain-os. It costs 0 tokens per session (1,696 once invoked), scanned A, original, MIT.

A work-planning command that recommends what to do next, using project context and stated limits such as available time or energy.

In plain words
What is it for?
Use it to choose a daily task for a specific project or for all projects, including when you have constraints like two hours or low energy.
Why use it?
It reduces the effort of choosing among competing tasks and explains the reason for the recommendation.

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/focus
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 focus

README.md
[![agentmods](https://agentmods.dev/badge/commands/brainos-hq/brain-os/focus.svg)](https://agentmods.dev/commands/brainos-hq/brain-os/focus)
Your own site
<a href="https://agentmods.dev/commands/brainos-hq/brain-os/focus"><img src="https://agentmods.dev/badge/commands/brainos-hq/brain-os/focus.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 1,696 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 $0.01696
Opus 5 $0.00000 $0.00848
Sonnet 5 $0.00000 $0.00339
Haiku 4.5 $0.00000 $0.00170

Measured 3d ago against content hash 861a547505e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

focus 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/focus.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brain OS : Focus Engine

"What should I work on today, and why?"

Not a dashboard. A judgment call backed by evidence.

REQUIRED FIRST READ

Before any tool call, read ~/.claude/brain-os/PROTOCOL.md. It governs tool routing for every Brain OS skill.

Input

Arguments: $ARGUMENTS (can be a project name like "brain os" or "ghost", OR a constraint like "only 2 hours" or "low energy today", OR both like "ghost, low energy")

Primary tool sequence

Step 0 — Resolve scope

Before calling focus_get, resolve whether this is a named/scoped focus or a global focus.

  1. If $ARGUMENTS contains --global or all, skip scope resolution → use General focus.
  2. If $ARGUMENTS names a project, call mcp__brain-os__context_resolve(user_message=$ARGUMENTS).
  3. If no project is named, obtain the client-visible workspace/folder path first (from client metadata or by running pwd in the active workspace), then call mcp__brain-os__context_resolve(user_message=$ARGUMENTS, files_touched=[current workspace/folder path]).
  4. If context_resolve returns entity_id with ask_user=false, use Named project with that entity.
  5. If context_resolve cannot resolve, but the client-visible folder is a known workspace mapping (for example my-repo folder → my-project entity), use that as a weak client-side folder signal.
  6. Only use General focus after scope resolution has actually run or after the user explicitly requested --global / all. Do not ask the user to clarify for a generic "focus" request unless the resolver reports an explicit ambiguity.

Important: this uses the client-visible workspace/folder path as an intent signal. It is not server-side process.cwd() inference. Explicit user project names always beat folder context.

Step 1 — Scan repo evidence (when a workspace path is known)

If you have a client-visible workspace/folder path, call mcp__brain-os__project_evidence_scan(root_path=<workspace path>, entity_id=<resolved entity, if any>) BEFORE focus_get.

Read the full file on GitHub · 134 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 · 134 lines · 0 tokens per session scan A 861a547505e5

Subscribe to this mod's changes

focus 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 1,696 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.