Writ
Hybrid RAG rule retrieval and workflow enforcement for Claude Code. A five-stage pipeline (BM25 + vector + graph traversal + two-pass ranking) retrieves the right coding rules for each task in under 1ms from a Neo4j knowledge graph,. 726x context reduction vs loading a full rulebook at 10K rules. A mode and gate state machine enforces workflow discipline at the tool-call boundary: - writes are blocked until plans and tests are approved. - Ships with 276 rules across 12 domains (Security, Clean
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Productivity — see all ranked ›
Work: Retrieval systems · Agent configuration
Who it is for: AI engineer · Agent operator
“writ query shows ranked output; states plugin installs leave the Bash allowlist missing”
- tashan score: 57.0
- Expertise: 86.0 (deep)
- Adoption: 1 repos
- Health: active
- GitHub stars: 163
- Contributors: 1
- License: MIT
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:infinri/writ/writ
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›