Install
$ agentstack add skill-cdeust-cortex-cortex-profile ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Profile — Cognitive Profiling and Methodology
Keywords
profile, methodology, cognitive style, work patterns, blind spots, how do I work, thinking style, domains, rebuild profile, my patterns, session history, cognitive, behavioral, persona
Overview
Cortex builds a cognitive profile from your Claude Code session history — how you explore code, which tools you prefer, what patterns you repeat, where you have blind spots, and how your style connects across different project domains. This profile is used to calibrate responses and surface relevant context.
Use this skill when: Starting a session (auto-injected via hook), wanting to understand your work patterns, or needing to rebuild profiles after significant new work.
Workflow
Step 1: Load Current Profile
cortex:query_methodology({
"cwd": "",
"first_message": ""
})
Returns:
- Cognitive style — Felder-Silverman dimensions (active/reflective, sensing/intuitive, visual/verbal, sequential/global)
- Entry patterns — How you typically start work in this domain
- Recurring patterns — Behavioral patterns that repeat across sessions
- Blind spots — Categories, tools, or patterns you tend to miss
- Connection bridges — Cross-domain analogies and structural similarities
- Hot memories — Most relevant active memories for this context
- Fired triggers — Prospective memories activated by the current context
Step 2: Explore Behavioral Features
Dive deeper into your behavioral profile:
cortex:explore_features({ "mode": "persona" })
Returns your 12-dimensional persona vector: exploration depth, tool diversity, session persistence, abstraction level, error recovery, etc.
Other exploration modes:
"mode": "features"— What behavioral dictionary features activate for this domain"mode": "attribution"— How the pipeline traces decisions back to behavioral signals"mode": "crosscoder"— Behavioral patterns that persist across different project domains
Step 3: View All Domains
cortex:list_domains({})
Shows all detected project domains with session counts, cognitive style per domain, and last activity timestamps.
Step 4: Rebuild Profiles
When profiles seem stale or after significant new work:
cortex:rebuild_profiles({})
Full rescan of ~/.claude/projects/ session history. Rebuilds all domain profiles, re-extracts patterns, re-classifies cognitive styles, and re-learns behavioral features.
Step 5: Record Session End
Normally automatic via hook, but can be called manually:
cortex:record_session_end({
"domain": "",
"summary": ""
})
Updates profiles incrementally via EMA (Exponential Moving Average) — no full rebuild needed.
Tips
- Profiles improve over time: The more sessions you have, the more accurate the cognitive profiling becomes
- Cross-domain bridges are powerful: If Cortex detects you use similar patterns in different projects, it surfaces those connections
- Blind spots are actionable: If Cortex says you under-use certain tools or miss certain categories, consider addressing those gaps
- Domain detection is automatic:
cortex:detect_domainclassifies the current working directory into a known domain — no manual tagging needed
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cdeust
- Source: cdeust/Cortex
- License: MIT
- Homepage: https://ai-architect.tools
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.