agent-brain-inject

A command that adds extra key-value information to document sections while they are being indexed. The information can come from a Python function or a JSON file.

In plain words
What is it for?
Use it to process documents with custom metadata, apply the same metadata to a folder, test an injector with a dry run, or set chunk size and overlap.
Why use it?
It lets searches and later processing retain context such as folder-specific labels that are not present in the document text itself.

Command

Part of the agent-brain-plugin plugin — 29 commands, 3 agents shipped together

Install

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.

agentmods
npx agentmods add commands/spillwavesolutions/agent-brain/agent-brain-inject
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain

Or install agent-brain-plugin, the plugin that ships this one along with the rest of its 29 commands, 3 agents.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,523 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 $0.00020 $0.01523
Opus 5 $0.00010 $0.00762
Sonnet 5 $0.00004 $0.00305
Haiku 4.5 $0.00002 $0.00152

Measured 3d ago against content hash 8756462f0798, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-brain-inject 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 3d 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-inject.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Injection

Purpose

Enrich chunk metadata during indexing using custom Python scripts or static JSON metadata. Injectors run after chunking but before embedding (Step 2.5 in the pipeline), so enriched metadata is stored alongside vectors in the index.

At least one of --script or --folder-metadata must be provided.

Usage

/agent-brain:agent-brain-inject <path> --script <script.py>
/agent-brain:agent-brain-inject <path> --folder-metadata <metadata.json>
/agent-brain:agent-brain-inject <path> --script <script.py> --folder-metadata <metadata.json>
/agent-brain:agent-brain-inject <path> --script <script.py> --dry-run

Parameters

Parameter Required Default Description
path Yes - Path to documents to index
--script No* - Python script exporting process_chunk(chunk: dict) -> dict
--folder-metadata No* - JSON file with static key-value metadata
--dry-run No false Validate injector against sample chunks without creating a job
--chunk-size No 512 Target chunk size in tokens
--chunk-overlap No 50 Overlap between chunks in tokens
--no-recursive No false Don't scan subdirectories
--include-code No false Include code files in indexing
--include-type No - File type presets (e.g., python,docs)
--languages No - Comma-separated language list for code
--code-strategy No ast_aware Code splitting: ast_aware or text_based
--include-patterns No - Additional glob include patterns
--exclude-patterns No - Additional glob exclude patterns
--generate-summaries No false Generate LLM summaries for better search
--force No false Force re-indexing (bypass manifest)
--allow-external No false Allow paths outside project directory
--json No false Output results as JSON

*At least one of --script or --folder-metadata is required.

Examples

Read the full file on GitHub · 193 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. 3d ago First seen · 193 lines · 20 tokens per session scan A 8756462f0798

Subscribe to this mod's changes

agent-brain-inject is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,523 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.