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/start.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/start)<a href="https://agentmods.dev/commands/starmynd-org/infinite-brain-harness/start"><img src="https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-harness/start.svg" alt="Measured on agentmods" 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 | $0.01384 |
| Opus 5 | $0.00000 | $0.00692 |
| Sonnet 5 | $0.00000 | $0.00277 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
start 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 7d 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.
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.
/start: set up (or wake up) this harness
Run this first on a new machine, and again each day. It establishes git access, clones your brains into
internal/, validates and registers them, and syncs. Work autonomously and verify each step before the
next; only stop for a sign-in the person must click, and tell them exactly what to click. Report each
step in one plain line. Set GIT_TERMINAL_PROMPT=0 so git fails fast instead of hanging on a credential
prompt.
Step 1: Git access (GitHub by default)
- Confirm git is installed and
user.nameanduser.emailare set. If not, set them (ask once). - Confirm the git host is reachable and authenticated. GitHub is the default backend: check
gh auth status, or an SSH key, or a credential helper. Ifghis not installed, point the person at https://cli.github.com/ (one installer per OS), then have them rungh auth loginand pick HTTPS plus browser sign-in; an SSH key per GitHub's docs works equally well. If a later clone fails with an auth error, it is this step unfinished: fix auth and retry. Never store a token in the repo. An alternate backend (a self-hosted or access-gated git host) only changes the remote URL and its sign-in; the rest of this command is unchanged.
Step 2: Know which brains to mount
- Read
.claude/brains.conf: onefolder = git-remote-urlper line, lines starting with#ignored. - If it exists, go to Step 3. If it is missing or empty, ask the person which case they are in:
- They already have brains (a team member joining an existing deployment): ask for the two
remotes, their shared brain (a company or department brain) and their individual brain
(named
individual-<their-name>), and write the file. - They are starting from zero (a solo learner, no existing repos): create both brains now, per
Step 2a. Every remote written to
brains.confmust be a repository the person can push to; never write the public starter's URL there..claude/brains.confis local and git-ignored; it holds no secrets, only repo URLs.
- They already have brains (a team member joining an existing deployment): ask for the two
remotes, their shared brain (a company or department brain) and their individual brain
(named
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.
- 7d ago First seen · 102 lines · 0 tokens per session scan A 2c71d5fccc9a
start is a command published in the GitHub repository starmynd-org/infinite-brain-harness (23 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,384 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.