agent-brain-jobs

agent-brain-jobs is a command for Claude Code from SpillwaveSolutions/agent-brain. It costs 15 tokens per session (1,263 once invoked), scanned A, original, MIT.

A command for monitoring background jobs that build or update an Agent Brain search index. It lists jobs, shows progress, displays job details, and can cancel a selected job.

In plain words
What is it for?
Use it to list queued jobs, watch live progress, inspect one job, review incremental-indexing details, or cancel a job by ID.
Why use it?
It makes work performed in a queue visible instead of leaving you unsure whether indexing is running or stuck. You can inspect or stop unwanted jobs.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/docs.

Part of the agent-brain plugin — 2 skills, 30 commands, 3 agents shipped together

Install

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.

Claude Code
/plugin marketplace add SpillwaveSolutions/agent-brain
Claude Code
/plugin install agent-brain

Made for: Claude Code.

Or install agent-brain, the plugin that ships this one along with the rest of its 2 skills, 30 commands, 3 agents.

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 agent-brain-jobs

README.md
[![agentmods](https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/agent-brain-jobs.svg)](https://agentmods.dev/commands/spillwavesolutions/agent-brain/agent-brain-jobs)
Your own site
<a href="https://agentmods.dev/commands/spillwavesolutions/agent-brain/agent-brain-jobs"><img src="https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/agent-brain-jobs.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,263 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.01263
Opus 5 $0.00008 $0.00632
Sonnet 5 $0.00003 $0.00253
Haiku 4.5 $0.00002 $0.00126

Measured 6d ago against content hash e42658eb9713, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-brain-jobs 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 6d 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.

agent-brain-plugin/commands/agent-brain-jobs.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Job Queue Management

Purpose

Monitor and manage async indexing jobs. Indexing runs in the background via a job queue — use this command to list jobs, watch progress, inspect details (including eviction summaries for incremental indexing), and cancel stuck or unwanted jobs.

Usage

/agent-brain:agent-brain-jobs
/agent-brain:agent-brain-jobs --watch
/agent-brain:agent-brain-jobs <job_id>
/agent-brain:agent-brain-jobs <job_id> --cancel

Parameters

Parameter Required Default Description
job_id No - Specific job ID to inspect
--watch / -w No false Poll queue every 3 seconds with live updates
--cancel / -c No false Cancel the specified job (requires job_id)
--limit / -l No 20 Maximum number of jobs to show
--json No false Output as JSON

Examples

# List all jobs
/agent-brain:agent-brain-jobs

# Watch queue with live updates
/agent-brain:agent-brain-jobs --watch

# Inspect a specific job
/agent-brain:agent-brain-jobs abc123

# Cancel a running job
/agent-brain:agent-brain-jobs abc123 --cancel

Execution

Based on the parameters:

List All Jobs

agent-brain jobs

Watch Queue (Live Updates)

agent-brain jobs --watch

Press Ctrl+C to stop watching.

Inspect Job Details

agent-brain jobs <job_id>

Cancel a Job

agent-brain jobs <job_id> --cancel

Expected Output

List:

Job ID    Status     Folder                  Created
abc123    completed  /home/user/docs         2026-03-05T12:00:00
def456    running    /home/user/src          2026-03-05T12:05:00
ghi789    queued     /home/user/tests        2026-03-05T12:06:00

Job Detail (with eviction summary):

Job Details: abc123

Status:    completed
Folder:    /home/user/docs
Created:   2026-03-05T12:00:00
Completed: 2026-03-05T12:00:45

Eviction Summary:
  Files added:     3
  Files changed:   2
  Files deleted:   1
  Files unchanged: 42
  Chunks evicted:  15
  Chunks created:  25

Read the full file on GitHub · 188 lines

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. 6d ago First seen · 188 lines · 15 tokens per session scan A e42658eb9713

Subscribe to this mod's changes

agent-brain-jobs is a command published in the GitHub repository SpillwaveSolutions/agent-brain (118 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,263 once invoked, about $0.0001 per session on Opus 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.