selectools: Skill for Claude Code

Bug Hunt

Deploy parallel QA sub-agents to find bugs. Scope: $ARGUMENTS

If no scope, default to "all".

Resolve Scope

• all → deploy 7 agents (one per subsystem below)
• agent → 1 agent: core loop, config, mixins, streaming, batch
• providers → 1 agent: all 5 providers, fallback, circuit breaker, _openai_compat
• tools → 1 agent: tool system, decorators, loader, registry, toolbox, MCP bridge
• rag → 1 agent: loaders, chunking, hybrid search, BM25, reranker, vector stores, embeddings
• memory → 1 agent: ConversationMemory, sessions, entity memory, knowledge graph, knowledge stores
• evals → 1 agent: evaluators, suite, report, regression, pairwise, snapshot, badges, CLI
• security → 1 agent: guardrails, audit, screening, coherence, policy, injection patterns

Agent Template

Each agent should read the source files for its subsystem, then look for:

1. Correctness Bugs

• Type mismatches — function signatures don't match callers (e.g. missing tools=None)
• Async/sync inconsistency — arun()/astream() missing features that run() has (pitfall #12)
• None handling — response_msg.content used without or "" guard (pitfall #7)
• Race conditions — shared mutable state in batch()/abatch() without locks. These are invisible to sequential tests. Key targets: circuit breakers, caches, vector stores, batch runners. Mental test: "what if two threads call this simultaneously?"
• Resource leaks — ThreadPoolExecutor() created per call instead of shared. Fix: module-level lazy singleton.

2. API Contract Violations

• Provider protocol — stream()/astream() not passing tools parameter (pitfall #1)
• ToolCall stringification — streaming paths converting ToolCall objects to strings (pitfall #2)
• Observer events — missing run_id in observer calls, or events not firing in all 3 loop methods
• StepType consistency — trace steps using string literals instead of StepType.ENUM_NAME
• _effective_model — any remaining self.config.model in _provider_caller.py (should all be self._effective_model)