infinite-brain-os: Command for Claude Code

.claude/commands/promote.md

promote is a command for Claude Code from starmynd-org/infinite-brain-os. It costs 42 tokens per session (1,285 once invoked), scanned A, original, MIT.

A command that moves a researched Markdown knowledge file from a personal repository into a department or company-wide repository. It updates the file’s metadata, checks links to other files, copies it to the target repository, and opens a pull request for review.

In plain words
What is it for?
Use it to submit personal notes, playbooks, or other knowledge files for wider organisational approval and reuse. It targets either a department repository or a company-canon repository.
Why use it?
It removes the manual work of adapting files to another repository’s rules and tracking cross-repository links. The source file must be marked as research, and the target repository must already be cloned nearby.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is starmynd-org/infinite-brain-os's own configuration. It tells Claude Code how to work on infinite-brain-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything infinite-brain-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to starmynd-org/infinite-brain-os. 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/starmynd-org/infinite-brain-os/main/.claude/commands/promote.md
Clone the repo
git clone --depth 1 https://github.com/starmynd-org/infinite-brain-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 promote

README.md
[![agentmods](https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-os/promote/github.svg)](https://agentmods.dev/commands/starmynd-org/infinite-brain-os/promote)
Your own site
<a href="https://agentmods.dev/commands/starmynd-org/infinite-brain-os/promote"><img src="https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-os/promote/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.

agentmods 80×15 button for promote

Your own site · 80×15
<a href="https://agentmods.dev/commands/starmynd-org/infinite-brain-os/promote"><img src="https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-os/promote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,285 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01285
Opus 5 $0.00021 $0.00642
Sonnet 5 $0.00008 $0.00257
Haiku 4.5 $0.00004 $0.00128

Measured 10d ago against content hash ecedb93224b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

promote 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 10d 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/promote.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/promote

Promote a node from this personal repo to a department or company-canon repo. The command rewrites the frontmatter to match the target repo's conventions, scans wikilinks for cross-repo references, copies the file into a working branch in the target repo's clone, and opens a pull request for the canonization gate to review.

Usage

/promote path/to/node.md target=department
/promote path/to/node.md target=company-canon

The first argument is the path to the node file in this repo (for example, knowledge/personal-operator/playbooks/attribution-standard.md). The target argument names which canon repo to promote into.

What this command does

  1. Reads the source node file and verifies it has lifecycle_state: research. Any other state is a refusal. scratch is too early. candidate and canon are already promoted. archive should be reopened first.
  2. Looks up the target repo path. Convention: the target repo is cloned as a sibling directory next to this personal repo (for example, ../acme-marketing/ for target=department or ../acme-company-canon/ for target=company-canon). If the sibling is not present, the command fails with a clear message ("clone the target repo as a sibling before running /promote").
  3. Delegates to skill-cross-repo-move for the file-move, frontmatter-rewrite, and wikilink-resolution mechanics.
  4. Opens a pull request against the target repo via gh pr create. PR title: promote: {node-id}. PR body: a summary of what is being promoted, the source node id, the source repo, and a checklist for the reviewer.

Frontmatter rewrite rules

The command applies these rewrites to the moved file:

Field Source value Target value
lifecycle_state research candidate
namespace personal-operator depends on target: canon-department or canon-company
local_path path in personal repo path in target repo

For nodes that already have richer frontmatter (visibility, owner_type, export_class), the command preserves those fields but normalizes them to the target repo's defaults (for example, visibility: workspace, owner_type: team for department, owner_type: company for company-canon).

Read the full file on GitHub · 99 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. 10d ago First seen · 99 lines · 42 tokens per session scan A ecedb93224b4

Subscribe to this mod's changes

promote is a command published in the GitHub repository starmynd-org/infinite-brain-os (248 stars, last pushed 14d ago), licensed MIT. It adds 42 tokens to every session and 1,285 once invoked, about $0.0002 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 2026-08-30.