conductai CLAUDE.md

Conduct

About

Owner: Sudhi Purpose: Building Conduct — a YAML playbook platform that turns AI agents into reusable team automations, with a FastAPI backend, Next.js canvas UI, Redis worker, and 39 playbooks covering GitHub, Slack, CI/CD, and incident response workflows.

Agent Work — Always-On Watchdog

When working on playbooks (apps/api/playbooks/), brain block prompts, turn budgets, or block chaining: activate /agent-builder skill. It enforces the review checklist for every agent capability change:

• Per-block max_turns set explicitly
• plan_fix (mode: single) before any mode: agentic block
• Memory blocks: recall_context before, record_outcome after
• Single-turn blocks output JSON only — no prose
• Proxy mode: one run_shell packs everything; sandbox: no GitHub API calls

---

RTK (Rust Token Killer) - Token-Optimized Commands

Golden Rule

Always prefix commands with rtk. If RTK has a dedicated filter, it uses it. If not, it passes through unchanged. This means RTK is always safe to use.

Important: Even in command chains with &&, use rtk:

# ❌ Wrong
git add . && git commit -m "msg" && git push

# ✅ Correct
rtk git add . && rtk git commit -m "msg" && rtk git push

RTK Commands by Workflow

Build & Compile (80-90% savings)

rtk cargo build         # Cargo build output
rtk cargo check         # Cargo check output
rtk cargo clippy        # Clippy warnings grouped by file (80%)
rtk tsc                 # TypeScript errors grouped by file/code (83%)
rtk lint                # ESLint/Biome violations grouped (84%)
rtk prettier --check    # Files needing format only (70%)
rtk next build          # Next.js build with route metrics (87%)

Test (60-99% savings)

rtk cargo test          # Cargo test failures only (90%)
rtk go test             # Go test failures only (90%)
rtk jest                # Jest failures only (99.5%)
rtk vitest              # Vitest failures only (99.5%)
rtk playwright test     # Playwright failures only (94%)
rtk pytest              # Python test failures only (90%)
rtk rake test           # Ruby test failures only (90%)
rtk rspec               # RSpec test failures only (60%)
rtk test <cmd>          # Generic test wrapper - failures only