cipherpowers

Interactive design refinement using Socratic method

Code review with structured feedback using specialised code-review-agent.

Systematic git commit with atomic commits and conventional messages

Execute implementation plans.

Create detailed implementation plans with bite-sized tasks

Implement findings from verification reports. Works with collation reports produced by `/verify`.

Retrospective summary capturing decisions and lessons learned

Test file path resolution in plugin agents

Dual-verification dispatcher for high-confidence verification

Meticulous principal software engineer. Use for development and code tasks.

Minimal implementation agent for plan execution. Follows plans literally, reports BLOCKED when stuck.

Meticulous principal engineer who reviews code. Use proactively for code review.

Systematic git committer with atomic commits and conventional messages.

Complex debugging specialist for production issues, multi-component systems, integration failures, and mysterious behavior requiring deep opus-level investigation

Verifies batch implementation matches plan specification exactly.

Validates review feedback against plan, prevents scope creep.

Test agent to verify file reference path resolution in plugin agents

Meticulous principal engineer who evaluates implementation plans.

Thorough researcher who explores topics from multiple angles.

Systematic collation of dual independent reviews to identify common issues, exclusive issues, and divergences with confidence levels (works for any review type)

Meticulous principal Rust engineer. Use for Rust development.

Minimal Rust implementation agent for plan execution. Follows plans literally, reports BLOCKED when stuck.

Technical documentation specialist for verification and maintenance.

Use boolean decision trees instead of imperatives for 100% compliance under pressure

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Systematic retrospective to capture decisions, lessons, and insights from completed work

Systematic commit process with pre-commit checks, atomic commits, and conventional commit messages

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Complete workflow for conducting thorough code reviews with structured feedback

Document complex domain knowledge as self-contained packages with multiple reading paths

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

Establish workflow boundary checklists with clear pass/fail criteria and escalation procedures

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Create symptom-based debugging documentation that matches how developers actually search for solutions

Use two independent agents for reviews or research, then collate findings to identify common findings, unique insights, and divergences

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Algorithmic decision tree for when to follow plan exactly vs when to report BLOCKED - prevents scope creep and unauthorized deviations

Two-phase workflow to keep project documentation synchronized with code changes

Use when creating, updating, or validating CLAUDE.md or AGENTS.md files - ensures size limits, progressive disclosure via docs/ references, multi-agent compatibility, and tool-first content

Set up or reorganize project documentation using intent-based structure (BUILD/FIX/UNDERSTAND/LOOKUP)

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches cipherpowers:code-review-agent subagent to review implementation against plan or requirements before proceeding

Thorough multi-angle research exploration with evidence requirements and structured output

Implement findings from verification reports with scope-based parallel workflow

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

Decision guide for choosing the right specialized agent for each task type

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Safe refactoring workflow for replacing old types with new type-safe implementations through integration-test-first, file-by-file migration with incremental verification

Algorithmic decision tree enforcing test-first development via boolean conditions instead of imperatives

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

Validate code review feedback against implementation plan to prevent scope creep and derailment

Verify batch implementation matches plan specification exactly - checks plan adherence, not code quality

Complete workflow for evaluating implementation plans before execution with quality checklist and structured feedback

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization