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.
npx agentmods add commands/spillwavesolutions/agent-brain/agent-brain-typesgit clone --depth 1 https://github.com/SpillwaveSolutions/agent-brainWhat 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 | $0.00012 | $0.00549 |
| Opus 5 | $0.00006 | $0.00275 |
| Sonnet 5 | $0.00002 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
agent-brain-types 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 2d 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
File Type Presets
Purpose
Show all available file type presets that can be used with the --include-type
flag during indexing. Presets are named groups of glob patterns that make it
easy to index specific categories of files without writing individual patterns.
Usage
/agent-brain:agent-brain-types
Examples
/agent-brain:agent-brain-types
Execution
Display all available file type presets:
agent-brain types list
# JSON output for scripting
agent-brain types list --json
Expected Output
Preset Extensions
python *.py, *.pyi, *.pyw
javascript *.js, *.jsx, *.mjs, *.cjs
typescript *.ts, *.tsx
go *.go
rust *.rs
java *.java
csharp *.cs
c *.c, *.h
cpp *.cpp, *.hpp, *.cc, *.hh
web *.html, *.css, *.scss, *.jsx, *.tsx
docs *.md, *.txt, *.rst, *.pdf
text *.md, *.txt, *.rst
pdf *.pdf
code *.py, *.pyi, *.pyw, *.js, *.jsx, ...
Use with: agent-brain index <path> --include-type <preset>
Output
Show the preset table and explain how to use presets with the index command. Provide examples of combining presets:
# Index only Python files
agent-brain index ./src --include-type python
# Index Python and documentation files
agent-brain index ./project --include-type python,docs
# Index all code files
agent-brain index ./repo --include-type code
# Combine presets with custom patterns
agent-brain index ./project --include-type typescript --include-patterns "*.json"
Notes
- Presets can be combined with commas:
--include-type python,docs - Presets can be combined with
--include-patternsfor custom patterns - The
codepreset is a union of all language presets - These presets are local (no server connection required)
- Use
agent-brain index --helpto see all indexing options
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.
- 2d ago First seen · 93 lines · 12 tokens per session scan A d72c8fb9fa4a
agent-brain-types is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 549 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.