infinite-brain-harness: Command for Claude Code

.claude/commands/workspace-help.md

workspace-help is a command for Claude Code from starmynd-org/infinite-brain-harness. It costs 0 tokens per session (443 once invoked), scanned A, original, MIT.

A command that explains a shared work environment where people keep knowledge, commands, and code in separate working areas. It also explains the everyday commands for starting work, saving changes, and synchronising them.

In plain words
What is it for?
Use it when someone needs a plain-language explanation of the workspace, its personal and shared areas, or the /start, /save, and /sync commands.
Why use it?
It helps newcomers understand where their work belongs, what can be changed safely, and which actions need review before they affect shared material.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is starmynd-org/infinite-brain-harness's own configuration. It tells Claude Code how to work on infinite-brain-harness 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-harness configures →

Reuse

Borrowing it

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

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 workspace-help

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/starmynd-org/infinite-brain-harness/workspace-help"><img src="https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-harness/workspace-help.svg" alt="Reviewed on agentmods" width="80" 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 443 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 $0.00000 $0.00443
Opus 5 $0.00000 $0.00221
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00044

Measured 9d ago against content hash 1a4eadafe060, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workspace-help 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 9d 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/workspace-help.md · 26 lines

What it actually says

/workspace-help: explain this harness

Explain the harness to the person in warm, plain words. No git jargon, no file-tree dumps. Adapt to what they ask; if they just typed /workspace-help, cover this:

  1. The brains. internal/ holds everything you own: the brains you work across, and any other repos you run. The brains are the folders you actually work in. The shared brain (a company or department brain) is the default, the canon everyone relies on. Your individual brain (individual-<your-name>) is where nothing you try can break anything for anyone. Rule of thumb: real shared work in the shared brain, ideas and experiments in your own.
  2. The everyday loop. /start sets up or wakes up the machine. /save puts your name on your work. /sync backs it up over git and pulls the latest from every brain.
  3. What is free and what needs review. Anything in your own brain is free; push it all day. Content you produce in the shared brain (outputs, session records) is free too. But a change to the shared brain's core (its knowledge, commands, or code) does not go straight to everyone; /sync puts it on a review branch and the brain's maintainer merges it. That protects everyone else who runs the same brain.
  4. Promotion. If something in your own brain turns out great, /promote-to-department packages it for review. If approved, everyone gets it.
  5. Where each brain's commands come from. /sync copies each brain's own commands, skills, and agents up into this harness, so they show up as slash commands here after a Claude Code restart. A copied command runs against its brain. .claude/CAPABILITIES.md lists what each brain holds so you know which one to reach for.

Close by asking what they want to do first, and route them to the right brain for it.

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. 9d ago First seen · 26 lines · 0 tokens per session scan A 1a4eadafe060

Subscribe to this mod's changes

workspace-help is a command published in the GitHub repository starmynd-org/infinite-brain-harness (23 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 443 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.