More screenshots
Works with the AI Agents you already use
Project Oracle: AGENTS.md & Agent Context Generator
Scans any codebase and writes AGENTS.md, CLAUDE.md or Obsidian notes with real commands, every framework, env var names and the landmines only the owner knows.
$12
About this skill
Point it at any repo and it produces the context file your coding agent actually needs.
What you get
AGENTS.md,CLAUDE.md, or an Obsidian note, generated from a real scan of the project- every detected framework (Next.js + Express + Socket.IO + React all show up, not just the first)
- real build/test commands read from
package.json,pyproject.toml,Makefile,pom.xml, monorepo children too - environment variable names from
.env.example(values never read,.envnever opened) - git context with credential-masked remotes, entry points, test frameworks and file counts
- an interview step that embeds what no scan can see: the project's purpose and its known landmines
Safe by design
- an existing
AGENTS.mdwithout oracle markers is never overwritten: the generator exits 2, shows the diff, and only rewrites with--forceafter you confirm (previous file kept as.bak) - generated sections live between
<!-- oracle:start -->/<!-- oracle:end -->, so later runs update in place and keep your hand-written text - no absolute paths and no secrets in the output, so the report is safe to share
Zero dependencies: pure Python 3.11+ standard library, Windows/macOS/Linux. Ships with a test suite and a lint/check script.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
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 3 days ago
- Software
Python 3.11+
- Optional
GitAn Obsidian vault (only for the vault step)