Initializes a hierarchical AGENTS.md knowledge base for a project. Use when a repo needs its structure, commands, and conventions documented for agents.
/init deep Generate hierarchical AGENTS.md files: root + complexity scored subdirectories, produced by a size formula driven dag map reduce ( scanners writers) so the main session's context stays flat at any repo size. Usage Workflow (High Level) 1. Size & route (main session) ONE eval cell measures the repo and computes the node formula. 2. Map (dag) scanner nodes extract per chunk facts into bounded file reports. 3. Reduce (dag) writer nodes own disjoint subtrees: score, write AGENTS.md…
Full body not shown for this license – view the source on GitHub →Copy a source-pinned command for your client. You run it yourself.
Destination: .claude/skills/init-deep · pinned to the source commit
# Run from your project root
git clone https://github.com/code-yeongyu/oh-my-openagent.git .skillboard-tmp
git -C .skillboard-tmp checkout 69e37f76baf3651170b61bf85ddad68142c35724
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/packages/omo-senpi/skills/init-deep" ".claude/skills/"
rm -rf .skillboard-tmpReview the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.
sudo apt update && sudo apt install -y gitnpm install -g @anthropic-ai/claude-code# Run from your project root
git clone https://github.com/code-yeongyu/oh-my-openagent.git .skillboard-tmp
git -C .skillboard-tmp checkout 69e37f76baf3651170b61bf85ddad68142c35724
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/packages/omo-senpi/skills/init-deep" ".claude/skills/"
rm -rf .skillboard-tmpDestination: .claude/skills/init-deep
Scanner static-checks@0.1.0 · commit 69e37f76baf3. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.
Contains commands that can irreversibly delete or overwrite data.
Evidence: rm -rf· fingerprint 3aa78388a06d8af1
Uses encoding/eval patterns that can hide executable content.
Evidence: [redacted]· fingerprint 1bbd174404efbce9