@codacy/gate-cli
v0.17.0
Published
CLI for GATE.md quality gate service
Readme
@codacy/gate-cli
CLI for GATE.md — a compounding quality system for AI-generated code.
Install
npm install -g @codacy/gate-cli
cd your-project
gate initThen open the project in Claude Code and run /gate-setup.
Permission denied?
If npm install -g fails with EACCES, your npm global directory needs fixing:
mkdir -p ~/.npm-global
npm config set prefix ~/.npm-global
echo 'export PATH=~/.npm-global/bin:$PATH' >> ~/.zshrc # or ~/.bashrc
source ~/.zshrc
npm install -g @codacy/gate-cliUpgrade to v0.16.0
npm install -g @codacy/gate-cli@latestExisting projects work without changes. New compound features (knowledge extraction, graph memory, pre-work injection) activate automatically. Run /gate-setup again to add the CLAUDE.md knowledge base pointer and reflection instructions.
Quick reference
| Command | Description |
|---------|-------------|
| Core | |
| gate init | Initialize GATE.md in current project |
| gate analyze | Run analysis on changed files (stop hook) |
| gate analyze --mode <mode> | Force analysis mode (standard/plan/debug/skip) |
| gate review --files <paths> | On-demand analysis (advisory) |
| gate status | Show project quality status |
| Auth & Config | |
| gate auth register | Register a project |
| gate hooks install | Wire Claude Code hooks |
| gate standard push | Upload project Standard |
| Knowledge | |
| gate reflect | Trigger knowledge extraction for current task |
| gate reflect --user-input "..." | Save a human reflection as a knowledge node |
| gate reflect --kind decision | Specify the node kind |
| Feedback | |
| gate feedback message "text" | Send general feedback |
| gate feedback finding <run-id> <pattern-id> <action> | Per-finding feedback |
| Tasks | |
| gate task list | List tasks |
| gate task close | Close the current task (triggers extraction) |
Skills (Claude Code)
| Skill | Description |
|-------|-------------|
| /gate-setup | Project configuration wizard |
| /gate-analyze | On-demand analysis |
| /gate-status | Project health dashboard |
| /gate-feedback | Feedback (general + per-finding) |
| /gate-learn | View and manage project knowledge |
| /gate-memory | Browse the knowledge graph |
| /gate-insights | Quality metrics + Standard evolution |
| /gate-reflect | Capture learnings after a task |
How it works
Prompt → inject knowledge → Agent works → gate analyze → reviewer + knowledge → PASS/FAIL
↓
extract learnings → .gate/memory/ (graph)
↓
next prompt starts smarterThe quality gate catches problems. The knowledge system prevents them from recurring. Every analysis run teaches the next one.
Requires Node.js 20+.
