Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mercurialsolo/claudectlWrote 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/mercurialsolo/claudectl/brain)<a href="https://agentmods.dev/commands/mercurialsolo/claudectl/brain"><img src="https://agentmods.dev/badge/commands/mercurialsolo/claudectl/brain/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/mercurialsolo/claudectl/brain"><img src="https://agentmods.dev/badge/commands/mercurialsolo/claudectl/brain.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 | $0.00016 | $0.00312 |
| Opus 5.5 | $0.00006 | $0.00125 |
| Sonnet 5.5 | $0.00003 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
brain 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 1mo 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
Control the claudectl brain's auto-approve/deny behavior for tool calls in this session.
Modes
on(default) — brain evaluates every tool call, auto-approves safe ones, denies dangerous ones. Low-confidence decisions fall through to normal permission prompts.off— brain is disabled. All tool calls go through Claude Code's normal permission flow. Use this when you want full manual control.auto— brain auto-approves all tool calls it considers safe, even with lower confidence. Use this when you trust the brain's judgment and want maximum speed.status— show the current mode without changing it.
What to do
Run claudectl --mode {{mode}} where {{mode}} is the argument the user provided (on, off, auto, or status). If no argument was provided, run claudectl --mode status.
After running the command, confirm the mode change to the user and briefly explain what it means:
off: "Brain disabled. Tool calls will go through normal permission prompts."on: "Brain active. Safe tool calls will be auto-approved, dangerous ones auto-denied."auto: "Brain in full auto mode. All decisions above the confidence threshold will execute without prompts."
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.
- 1mo ago First seen · 24 lines · 16 tokens per session scan A 030807b5a59a
brain is a command published in the GitHub repository mercurialsolo/claudectl (202 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 312 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
computer
Drive a computer's screen, mouse, and keyboard.
unifly-audit
Read-only audit of UniFi WiFi security, firewall policy, and network isolation.
unifly-status
Read-only health check of UniFi infrastructure, including devices and alerts.
afsr
Review feature spec - improve the spec itself before implementation (shortcut for feature-spec-review).
aigon-feedback-triage
Run a triage loop for one feedback item with explicit human confirmation before writes.
check
Audit a .nika workflow before it runs — findings with their NIKA-XXXX codes, cost envelope, permits.