cortex-recommend

A command that reviews a knowledge graph, which is a collection of connected notes, for ways to improve its organisation and usefulness. It looks for duplicate, overly scattered, and possibly outdated information.

In plain words
What is it for?
Use it to find highly similar notes to merge, groups that need a summary, stale low-connection notes, and useful project conventions missing from the graph.
Why use it?
It helps reduce repeated notes and identify knowledge that may need updating or combining. This can make the graph clearer and reduce the amount of context an agent must process.

Command for Claude Code

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/peaky8linders/claude-cortex/cortex-recommend
Clone the repo
git clone --depth 1 https://github.com/Peaky8linders/claude-cortex

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 212 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 $0.00008 $0.00212
Opus 5 $0.00004 $0.00106
Sonnet 5 $0.00002 $0.00042
Haiku 4.5 $0.00001 $0.00021

Measured 2d ago against content hash 4d7567067bbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortex-recommend 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.

.claude/commands/cortex-recommend.md · 30 lines

What it actually says

Generate optimization recommendations from the Cortex knowledge graph.

First, run consolidation analysis:

cd ~/.claude/knowledge && python -m brainiac consolidate

Then run stats for context:

cd ~/.claude/knowledge && python -m brainiac stats

Analyze the results and present recommendations sorted by priority:

  1. Merge candidates (>0.9 similarity) — nodes that should be combined to reduce redundancy
  2. Abstraction candidates (3+ similar nodes) — clusters that need a higher-level summary node
  3. Stale nodes (60+ days, few connections) — knowledge that may be outdated

For each recommendation, provide:

  • Priority level (critical / optimize / suggest)
  • Specific action to take
  • Estimated impact (token savings, clarity improvement)

Also check the current project's CLAUDE.md for any conventions that could be captured as patterns but aren't in the graph yet.

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. 2d ago First seen · 30 lines · 8 tokens per session scan A 4d7567067bbf

Subscribe to this mod's changes

cortex-recommend is a command published in the GitHub repository Peaky8linders/claude-cortex (11 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 212 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.