Skill Claude CodeCodex
Use first for creative work—technical or everyday—when a brief is incomplete or intent is implicit and success depends on taste, voice, feeling, or human experience. Also trigger when literal compliance may lose the point. Do not wait for explicit creative wording. Skip factual lookup, mechanical or exact tasks, and…
Plugin Claude Code
Full dev lifecycle: idea → prompt → plan → run → site audit → deep research. Multi-agent task executor with bd integration.
Agent
Requirements traceability specialist for bishx-plan. Systematically maps every requirement from CONTEXT.md to plan tasks. Finds orphaned requirements and scope creep.
Agent
Final quality gate for bishx-plan. Aggregates all actor feedback, scores with weighted dimensions, validates against cross-actor ceilings, and issues APPROVED/REVISE/REJECT verdict.
Agent
Plan executability validator for bishx-plan. Mentally executes the first tasks as a fresh Claude session and reports where it gets stuck.
Agent
Inter-task compatibility specialist for bishx-plan. Validates data flow between tasks, dependency graph integrity, shared resource conflicts, and interface contracts.
Agent
Performance anti-pattern detection specialist for bishx-plan. Checks for N+1 queries, missing indexes, algorithm complexity, memory leaks, and caching opportunities.
Agent
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans for bishx-plan. Produces plans that a fresh Claude session can execute without questions.
Agent
Persistent critical review agent for bishx-research. Performs iterative multi-level review of research drafts, finding mirages, gaps, coherence issues, depth problems, and bias.
Agent
Opus-level deep dive agent for bishx-research. Goes deeper on complex areas, resolves contradictions, and verifies low-confidence critical findings from Wave 1 investigators.
Agent
Deep investigation agent for bishx-research. Researches assigned sub-topics with embedded skepticism, source verification, and multi-tier confidence tagging.
Agent
Rapid landscape reconnaissance for bishx-research. Maps sources, classifies complexity, recommends investigation strategy before deep research begins.
Agent
Synthesis and report writing specialist for bishx-research. Combines verified findings into a structured, coherent research report organized by analytical lenses.
Agent
Fact-checking specialist for bishx-research. Verifies every claim against its cited source, detects mirages, resolves confidence inflation, and validates source accessibility.
Agent
Deep research agent for bishx-plan. Investigates codebase architecture, external docs, APIs, schemas, and library compatibility with maximum depth and confidence tagging.
Agent
Security vulnerability detection specialist for bishx-plan. Checks OWASP Top 10, threat modeling, auth boundaries, input validation, and sensitive data handling.
Agent
Mirage detection specialist for bishx-plan. Verifies plan claims against codebase reality and external facts. Catches assumptions masquerading as facts.
Agent
TDD compliance reviewer for bishx-plan. Ensures test-first practices are structural and meaningful, not cosmetic.
Command
Stop the active bishx-run or bishx-site session gracefully.
Command
Analyze the project and suggest new features worth building.
Command
Scan codebase and fill/update CLAUDE.md and AGENTS.md with real project data.
Command
Create CLAUDE.md and AGENTS.md templates in the project root.
Command
Import bishx-plan into bd (beads) as Epic → Feature → Task hierarchy with dependencies. Handles existing tasks gracefully.
Command
Start automated iterative planning with 10-actor parallel verification pipeline (up to 10 iterations).