Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add SpillwaveSolutions/agent-brain/plugin install agent-brainWrote 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/spillwavesolutions/agent-brain/agent-brain-stop)<a href="https://agentmods.dev/commands/spillwavesolutions/agent-brain/agent-brain-stop"><img src="https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/agent-brain-stop/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/spillwavesolutions/agent-brain/agent-brain-stop"><img src="https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/agent-brain-stop.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 | $0.00013 | $0.00842 |
| Opus 5.5 | $0.00005 | $0.00337 |
| Sonnet 5.5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
agent-brain-stop 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stop Agent Brain Server
Purpose
Gracefully stops the Agent Brain server running for the current project. Sends SIGTERM and waits for graceful shutdown. If --force is specified and the process does not exit within the timeout, sends SIGKILL.
Usage
/agent-brain:agent-brain-stop [--path <dir>] [--force] [--timeout <sec>] [--json]
Parameters
| Parameter | Required | Default | Description |
|---|---|---|---|
| --path, -p | No | auto-detect | Project path |
| --force, -f | No | false | Force stop with SIGKILL if SIGTERM fails |
| --timeout | No | 10 | Graceful shutdown timeout in seconds |
| --json | No | false | Output as JSON |
Execution
# Stop server for current project
agent-brain stop
# Force stop if graceful shutdown fails
agent-brain stop --force
# Stop a specific project's server
agent-brain stop --path /my/project
# JSON output for scripting
agent-brain stop --json
Expected Output (Success)
Stopping server (PID 12345)...
Server stopped gracefully (PID 12345).
JSON Output (Success)
{
"status": "stopped",
"message": "Server stopped gracefully",
"pid": 12345,
"project_root": "/home/user/my-project"
}
Expected Output (Server Not Running)
No server running for this project.
Force Kill Output
Stopping server (PID 12345)...
Graceful shutdown timeout, sending SIGKILL...
Server force killed (PID 12345).
Output
Format the result as follows:
Server Stopped Successfully:
- Confirm the server was stopped
- Report the PID that was terminated
- State files and registry entry are cleaned up automatically
Server Not Running:
- Inform the user no server was found
Server Already Stopped:
- If the process is no longer alive but state files exist, they are cleaned up
Error Handling
| Error | Cause | Resolution |
|---|---|---|
| No server running | Server already stopped or never started | No action needed |
| Permission denied | Process owned by different user | Run with appropriate permissions |
| Graceful shutdown timeout | Process unresponsive within timeout | Use --force to send SIGKILL |
| No Agent Brain state found | State directory missing | Project may not be initialized |
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 · 142 lines · 13 tokens per session scan A 67fb9b0cb766
agent-brain-stop is a command published in the GitHub repository SpillwaveSolutions/agent-brain (119 stars, last pushed 27d ago), licensed MIT. It adds 13 tokens to every session and 842 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
tools
Manage MCP tools with natural language commands to list, enable, and disable tools and tool groups.
evolve-lite-subscribe
Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.
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.