doodledood/claude-code-plugins
21 subagents
Subagent
change-intent-reviewerAdversarially analyze whether code, prompt, or config changes achieve their stated intent. Reconstructs change intent from diff context, then systematically attacks the logic to find behavioral divergcode-bugs-reviewerAudit code changes for mechanical defects — runtime failures, resource issues, and structural code flaws. Focuses on defects detectable from code patterns (race conditions, resource leaks, edge cases,code-coverage-reviewerVerify that code changes have adequate test coverage by proactively enumerating edge cases from the code's logic. Analyzes the diff, derives specific test scenarios with concrete inputs and expected ocode-design-reviewerAudit code for design fitness issues — whether code is the right approach given what already exists in the framework, codebase, and configuration systems. Identifies reinvented wheels, misplaced respocode-maintainability-reviewerUse this agent when you need a comprehensive maintainability audit of recently written or modified code. Focuses on code organization: DRY violations, coupling, cohesion, consistency, dead code, and acode-simplicity-reviewerAudit code for unnecessary complexity, over-engineering, and cognitive burden. Identifies solutions more complex than the problem requires — not structural issues like coupling or DRY (handled by maincode-testability-reviewerAudit code for testability issues. Identifies code requiring excessive mocking, business logic buried in IO, non-deterministic inputs, and tight coupling that makes verification hard. Use after implemcontext-file-adherence-reviewerVerify that code changes comply with context file instructions (CLAUDE.md, AGENTS.md, GEMINI.md) and project standards. Audits pull requests, new code, and refactors against rules defined in the projecontracts-reviewerVerify API and interface contract correctness with evidence. Checks both outbound (code calls external/internal APIs correctly per documentation) and inbound (changes don't break consumers of your intcriteria-checkerRead-only verification agent. Validates a single criterion using any available tool (bash, file inspection, web fetch, MCP servers, CLI tools). Returns PASS / FAIL / BLOCKED with evidence.define-session-analyzerAnalyze a single /define session transcript to extract user preference patterns. Spawned by learn-define-patterns skill for parallel per-session analysis.docs-reviewerAudit documentation and code comments for accuracy against recent code changes. Performs read-only analysis comparing docs to code, producing a report of required updates without modifying files. Use github-pr-lifecycleRead-only inspection agent for a single GitHub PR — checks CI, review threads, description sync, and mergeability; reports PASS or FAIL with per-gate findings. Never invokes the merge button. Use whenoperational-readiness-reviewerAudit code and configuration changes for concrete runtime, deployment, rollback, retry, scale, and CI risks. Use when diffs touch infrastructure, environment configuration, secrets, public endpoints, prompt-compression-verifier../../claude-plugins/prompt-engineering/agents/prompt-compression-verifier.mdprompt-reviewer../../claude-plugins/prompt-engineering/agents/prompt-reviewer.mdprompt-token-efficiency-verifier../../claude-plugins/prompt-engineering/agents/prompt-token-efficiency-verifier.mdprose-value-reviewerAudit code comments and repo-resident doc files for prose value. Doc-file scope adapts to whatever documentation layout the project uses (READMEs anywhere, *.md at the repo root, plus *.md in whateverslack-pollerNarrate new Slack messages in a channel or thread since a cursor. Returns a natural-language story of what was said, or a clear statement when there is nothing new. Use when a parent agent polls Slacktest-quality-reviewerVerify that tests for code changes are both PRESENT (coverage) and VALIDATING (not tautological). Derives test scenarios from source logic, reports coverage gaps with concrete inputs and expected outptype-safety-reviewerAudit code for type safety issues across typed languages (TypeScript, Python, Java/Kotlin, Go, Rust, C#). Identifies type holes that let bugs through, opportunities to make invalid states unrepresenta