More screenshots
Works with the AI Agents you already use
Project Brain Map
Agents re-discover your codebase's shape every session — unless the shape lives on disk.
$7.99
Project Brain Map
Example session with this skill installed
"Our agents re-discover the repo structure every session and our architecture docs are 3 months rancid." → init declares 8 real files, build generates the graph + viewer, the pre-commit hook starts failing on drift instead of letting the doc rot.
- Read your context and instructions
- Compiled the project brain map
Connects securely to your tools. The creator never sees your data.
About this skill
Agents re-discover your codebase's shape every session — unless the shape lives on disk. This skill gives every project a small, honest architecture graph: declared nodes, live line counts, one glanceable HTML page, and a staleness gate that turns "stale docs" from a polite wish into a red exit code.
Warmed by real use across 7 repositories before publishing.
A graph nobody keeps fresh is a lie. So the map is declared by hand (what you verified), recomputed on every build (what you can measure), and gated before commits (what you cannot forget).
- init scaffolds
ops-brain/brain-map.json(a tiny declaration: nodes withid / file / roleand edges withfrom / to / type / via) plusARCHITECTURE.html. - build reads the declaration, verifies EVERY declared file exists (an
invented map fails loudly with the list), recomputes line counts, writes
ops-brain/brain-graph.json, and injects the fresh graph into the viewer (works fromfile://, no server needed). - check recompute reality and compares with the stored graph: missing files, per-node line drift (default tolerance ±5). Designed for your pre-commit hook:
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
The map is curated, not auto-scanned — it reflects your declared attention (that is the feature: no noise). check measures line drift and vanished files, not renames with unchanged line counts. The HTML viewer is deliberately plain and dependency-free.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 16 days ago
- Software
Node.js
Any modern Node.js version works, with no npm install.
Permissions
File Scopes
Purpose: maintain a curated, honest architecture graph per project. brain_map.js is pure Node stdlib: init scaffolds, build verifies every declared file exists (fails loudly on invented nodes) and recomputes line counts, check is a staleness gate for pre-commit hooks (exit 1 on drift). No network connections, no command execution inside the generator, no access to environment variables or credentials. All writes stay inside the project's ops-brain folder.