cortex-explore-memory

A skill for examining the state of Cortex, a system that stores an AI assistant's memories and knowledge. It reports stored memories, topic coverage, relationships, and knowledge gaps.

In plain words
What is it for?
Use it to check memory health, assess coverage of a project or topic, find missing knowledge, and diagnose sparse areas.
Why use it?
It helps show what the memory system knows, where information is weak, and whether stored knowledge is becoming outdated.

Skill for Claude CodeCodex

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 skills/cdeust/cortex/cortex-explore-memory
Any agent
npx skills add cdeust/Cortex --skill cortex-explore-memory
Clone the repo
git clone --depth 1 https://github.com/cdeust/Cortex

Made for: Claude Code, Codex.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 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 $0.00091 $0.00683
Opus 5 $0.00046 $0.00342
Sonnet 5 $0.00018 $0.00137
Haiku 4.5 $0.00009 $0.00068

Measured yesterday against content hash a03a2d050ab9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortex-explore-memory 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 yesterday.

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.

skills/cortex-explore-memory/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explore Memory — Diagnostics, Gaps, and Coverage

Keywords

memory stats, diagnostics, coverage, gaps, what am I missing, memory health, knowledge gaps, weak areas, isolated entities, sparse domains, how much do I know, memory overview, system status, knowledge assessment

Overview

Understand the state of your memory system — what's stored, what's missing, what's decaying, and where knowledge is strong or weak. This skill combines multiple diagnostic tools to give you a complete picture.

Use this skill when: Starting a new project phase, after a long break, or when you want to understand what Cortex knows and doesn't know about a topic.

Workflow

Step 1: Quick Health Check

Get system-level diagnostics:

cortex:memory_stats({})

Returns: total memories, heat distribution, store type breakdown (episodic vs semantic), entity count, relationship count, average confidence, and decay statistics.

Step 2: Assess Knowledge Coverage

Score how well a topic or project is covered:

cortex:assess_coverage({
  "domain": "<project or topic>",
  "query": "<specific area to assess>"
})

Returns a 0-100 coverage score with specific recommendations on what to document or remember next.

Step 3: Detect Knowledge Gaps

Find isolated entities, sparse domains, and temporal drift:

cortex:detect_gaps({
  "domain": "<optional domain filter>"
})

Returns:

  • Isolated entities — entities mentioned but not connected to memories
  • Sparse domains — project areas with few memories
  • Temporal gaps — periods with no memory activity (potential knowledge loss)
  • Orphan clusters — groups of memories disconnected from the main knowledge graph

Step 4: Validate Against Filesystem

Check if memories reference files/paths that still exist:

cortex:validate_memory({
  "directory": "<project root>"
})

Flags stale memories that reference deleted files, moved modules, or renamed functions — keeping the knowledge base accurate.

Read the full file on GitHub · 95 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. yesterday First seen · 95 lines · 91 tokens per session scan A a03a2d050ab9

Subscribe to this mod's changes

cortex-explore-memory is a skill published in the GitHub repository cdeust/Cortex (71 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 683 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

food-order

Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.

Bitterbot-AI/bitterbot-desktop · 53 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

genesis-development

This skill should be used when developing, debugging, refactoring, or building Genesis itself — tasks like "fix this in Genesis", "add a new MCP tool", "wire up the runtime", "Genesis won't start", "create a worktree", "debug the bridge", or "add a capability". Applies to any task modifying files under src/, .claude/…

WingedGuardian/GENesis-AGI · 115 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens

agoragentic-transaction-assurance

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…

rhein1/agoragentic-integrations · 65 tokens

linkding

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

jmagar/claude-homelab · 69 tokens