A command that runs a short predictive simulation for a specific high-stakes situation. It examines likely developments up to two steps ahead and stops when there is not enough information about the people involved.

Use it to examine situations raised in a daily digest, a one-to-one meeting brief, or a topic escalation, and to draft a decision record.

It helps structure thinking about uncertain situations without presenting guesses as precise probabilities or automatically choosing what to do.

How jaroslavsoucek-art/Giovanni configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jaroslavsoucek-art/Giovanni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/commands/branch-out.md

Clone the repo

git clone --depth 1 https://github.com/jaroslavsoucek-art/Giovanni

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jaroslavsoucek-art/giovanni/branch-out/github.svg)](https://agentmods.dev/commands/jaroslavsoucek-art/giovanni/branch-out)

Your own site

<a href="https://agentmods.dev/commands/jaroslavsoucek-art/giovanni/branch-out"><img src="https://agentmods.dev/badge/commands/jaroslavsoucek-art/giovanni/branch-out/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/jaroslavsoucek-art/giovanni/branch-out"><img src="https://agentmods.dev/badge/commands/jaroslavsoucek-art/giovanni/branch-out.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,597 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.01597
Opus 5	$0.00012	$0.00798
Sonnet 5	$0.00005	$0.00319
Haiku 4.5	$0.00002	$0.00160

Measured 11d ago against content hash bbba3cdabd1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

branch-out 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 11d 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/branch-out.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/branch-out

Run an active predictive simulation on a high-stakes situation surfaced by today's digest, a 1:1 brief, or a topic-shard escalation. This command is a thin shell — the 8 binding principles (no percentages, max horizon t+2, hard stop on shallow actors, no recommended move, canonical names from registry, invisible shadow hypotheses, adversarial lookback, decision records draft only) live in the prediction-runtime agent. This file is the invocation contract.

Usage

/branch-out <situation-slug>            # required positional
/branch-out <situation-slug> --from-digest    # use today's digest as triage source

Example: /branch-out fundraise-followup-call-2026-05-27

Argument syntax

Arg	Type	Default	Meaning
`<situation-slug>`	positional, required	—	Kebab-case identifier for the situation. Must match the slug surfaced in today's `/digest` "Active branch-out candidates", a brief reference, or a topic shard escalation. Used as primary key in `memory/branch-out/<today>-<slug>.md` and the decision record draft.
`--from-digest`	boolean flag	off	Pull triage context from today's `/digest` rendered output (must have run earlier today). Without this flag, the orchestrator infers situation context from existing files or asks the principal.

If <situation-slug> missing → STOP: ERROR: /branch-out requires <situation-slug>. Usage: /branch-out <kebab-case-slug>.

Pre-flight (binding — STOP on failure)

Before spawning prediction-runtime:

CWD check. Working directory is a Giovanni repo (presence of memory/triage-heuristic.yaml + knowledge/<constitution>.md). Otherwise STOP with diagnostic.
Agent definition present. .claude/agents/prediction-runtime.md exists. Missing → STOP: ERROR: prediction-runtime agent definition missing. Cannot run /branch-out.
Triage heuristic present. memory/triage-heuristic.yaml parses. Missing or malformed → STOP: ERROR: memory/triage-heuristic.yaml missing or unparseable. Predictive layer is not configured.
Canonical moves registry present. memory/branch-out/canonical-moves.md exists. Missing → STOP: ERROR: memory/branch-out/canonical-moves.md missing. Register canonical move names per docs/prediction.md before running /branch-out.
No stale draft for today. If memory/decisions/<today>-<situation-slug>.md already exists with status: draft, surface a warning (not a STOP): WARN: Decision draft for <slug> already exists from earlier run. The new run will overwrite. Proceed? [y/N]. Default = abort.

Read the full file on GitHub · 102 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.

11d ago First seen · 102 lines · 24 tokens per session scan A bbba3cdabd1c

Subscribe to this mod's changes

branch-out is a command published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 1,597 once invoked, about $0.0001 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.

Claude Code Planning agent-framework agentic-ai ai-agents anthropic chief-of-staff

Giovanni: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/branch-out

Usage

Argument syntax

Pre-flight (binding — STOP on failure)

What this file has done since we first saw it

Other commands, from other repositories

code-review-swarm

multi-repo-swarm

release-manager

release-swarm

repo-architect

swarm-issue