Read-only codebase analysis and implementation planning. Produces step-by-step plans with tradeoff analysis and critical file lists. Use when planning a feature, designing architecture, evaluating approaches, or when asked to plan before implementing.
Adversarial verification of code changes. Tries to break implementations rather than confirm they work. Produces structured PASS/FAIL/PARTIAL verdicts with evidence. Use when verifying code changes, after non-trivial implementations, before reporting task completion, or when asked to check if something works.
Create structured, thorough summaries of conversations and work sessions. Preserves technical details, code changes, errors, and pending tasks for continuity. Use when summarizing a session, creating handoff notes, compacting context, or when asked to recap progress.
Enforce scoped, minimal, correct code changes. Prevents gold-plating, speculative abstractions, and unsolicited refactoring. Use when writing code, fixing bugs, adding features, or making any code changes to ensure disciplined, focused implementation.
Optimal tool selection, parallelism, and safety for coding tasks. Covers the IDE tool preference matrix, parallel vs sequential execution, git safety, sandbox awareness, and file operation hygiene. Use when writing tool calls, running commands, managing files, or performing git operations.
Create reusable skills and agent configurations through structured interview and template generation. Covers SKILL.md authoring, agent persona design, and structured output contracts. Use when creating a new skill, designing an agent, capturing a repeatable process, or when asked to "skillify" a workflow.
Patterns for safe autonomous operation with allow/deny rule composition, risk classification, pacing, and focus-aware behavior. Use when operating autonomously, configuring auto-mode permissions, or when the user wants hands-off task execution with safety guardrails.
Security analysis for code changes and requests. Classifies activities as permitted, forbidden, or requiring authorization context. Covers OWASP risks, boundary validation, and dual-use tool guidance. Use when reviewing code for security, handling security-related requests, performing threat modeling, or when asked to assess security posture.