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/peaky8linders/claude-cortex/brainiacgit clone --depth 1 https://github.com/Peaky8linders/claude-cortexWhat 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 | $0.00009 | $0.00404 |
| Opus 5 | $0.00005 | $0.00202 |
| Sonnet 5 | $0.00002 | $0.00081 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
brainiac 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.
What it actually says
/brainiac — Query and Manage the Knowledge Graph
You interact with the Brainiac knowledge graph engine. The graph stores all cross-project learnings as interconnected nodes with semantic, temporal, causal, and entity edges.
System Location
- Engine:
~/.claude/knowledge/brainiac/ - Graph data:
~/.claude/knowledge/graph/(nodes.json, edges.json, embeddings.npz) - Views:
~/.claude/knowledge/views/(auto-generated markdown)
Command
Parse the user's message after /brainiac and run the appropriate command.
Important: Only accept these known subcommands: search, stats, add, link, consolidate, render, quality. Reject any other input to prevent command injection.
cd ~/.claude/knowledge && python -m brainiac <subcommand> [args]
Available Operations
If no arguments provided, show this help:
search "QUERY"— Semantic search across all nodesstats— Graph overview (node counts, edge counts, quality)add <type> "content"— Add node (types: pattern, antipattern, workflow, hypothesis, solution, decision)link <id1> <id2> <relation>— Link nodes (relations: semantic, temporal, causal, entity)consolidate— Find merge/prune candidatesrender— Regenerate markdown viewsquality— Get quality score (0-100)
When to Use
- Before starting work: search for relevant patterns or solutions
- During debugging: search for known solutions
- When making architecture decisions: search for prior decisions
- When reviewing: check antipatterns
- Periodically: run consolidate to keep the graph healthy
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.
- 3d ago First seen · 43 lines · 9 tokens per session scan A 84caef92579a
brainiac is a command published in the GitHub repository Peaky8linders/claude-cortex (11 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 404 once invoked, about $0.0000 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.