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.
curl -O https://raw.githubusercontent.com/starmynd-org/infinite-brain-harness/main/.claude/commands/workspace-help.mdgit clone --depth 1 https://github.com/starmynd-org/infinite-brain-harnessWrote 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.
[](https://agentmods.dev/commands/starmynd-org/infinite-brain-harness/workspace-help)<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.
<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>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 | $0.00000 | $0.00443 |
| Opus 5 | $0.00000 | $0.00221 |
| Sonnet 5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00044 |
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.
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:
- 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. - The everyday loop.
/startsets up or wakes up the machine./saveputs your name on your work./syncbacks it up over git and pulls the latest from every brain. - 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;
/syncputs it on a review branch and the brain's maintainer merges it. That protects everyone else who runs the same brain. - Promotion. If something in your own brain turns out great,
/promote-to-departmentpackages it for review. If approved, everyone gets it. - Where each brain's commands come from.
/synccopies 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.mdlists 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.
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.
- 9d ago First seen · 26 lines · 0 tokens per session scan A 1a4eadafe060
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.