
Use when: full dev cycle branch->plan->implement->review->PR->merge
Use when: running CSA-driven code review, independent model selection
--- name = "csa-setup" version = "0.1.0" description = "Install CSA, Weave, and coding workflow patterns for AI agent bots" homepage = "https://github.com/RyderFreeman4Logos/cli-sub-agent" target = "agent-bots" --- # CSA Setup > Installation guide for AI agent bots (openclaw, Moltis, etc.) to set up > CSA and Weave with optional coding workflow patterns. ## Skill Files | File | Description | |------|-------------| | **skill.md** (this file) | Installation and setup guide | | **skills/AGENTS.
Use when: converting TODO plan or open GitHub issues into deterministic execution checklist
Use when: deep per-crate code audit, Chinese documentation generation
Use when: committing with pre-commit review, authorship-aware fix-retry
Reviewer CSA for fact-checking Writer outputs against source code
Use when: reviewing GitHub PR via gh CLI, scale-adaptive strategy
Expert diagnosis for Tokio/async Rust issues including deadlocks, task leaks, performance bottlenecks, and cancellation safety
Adversarial security analysis expertise for identifying vulnerabilities before attackers do
Use when: per-file AGENTS.md compliance audit with Chinese reports
Use when: creating CSA pattern (PATTERN.md + skill + workflow.toml)
Use when: merged PR had HIGH/CRITICAL findings that represent a bug class — extracts reusable coding rule
Recover main-agent context after `/clear`, `/compact`, or lost local thread state by using `csa recall` against recorded Claude main sessions.
Use when: three-layer manager-employee orchestration for delegation
Use when: review found 2+ independent findings in different files, fix phase can parallelize RECON
Split monolith project documentation (CLAUDE.md, etc.) into condensed summary + reference detail files following AGENTS.md pattern
Use when: committing code with security audit, tests, review gates
Comprehensive guide for professional Rust development combining implementation expertise, architectural depth, and project standards
Comprehensive test design for Rust projects following Core-first TDD and test pyramid principles
Use when: CSA hits operational error, filing structured GitHub issue
Use when: generating technical blogs from codebase-audit results
Use when: adversarial multi-tool debate for strategy, tier escalation
Run CSA project migrations to update config and workflow files to the current version
Use when: pre-commit security audit (tests, vulns, code quality)
Launch long-running commands (>4 min) via nohup and poll at kv_cache.long_poll_seconds (default 240s) to keep KV cache warm.
Use when: creating, auditing, or optimizing repository quality gates (git hooks, pre-commit checks, CI guards, merge protection)
Use when: iterative review-fix loop until csa review --diff is clean
Use when: PR review loop with cloud bot, arbitration, and merge
Use when: executing tasks via csa run/review/debate, session mgmt
Use when running a non-blocking CSA background code health scan that uses csa health and csa tokuin estimate to propose refactoring GitHub issues for files over token or complexity thresholds.
Use when: creating TODO plan with debate-enhanced CSA reconnaissance, including epic decomposition for large tasks
Clear, practical documentation for APIs, README, architecture decisions, and changelogs
Writer CSA for deep crate analysis — generates README, review report, blog, and facts.toml
Use when: legacy alias, redirects to dev2merge pipeline