Solo-Code-Harness

Bắt buộc khai báo độ phức tạp Big-O và cấu trúc dữ liệu trước khi viết thuật toán.

Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

Prevent commits that skip pre-commit hooks (--no-verify, -n). Auto-loads when git commit with bypass flags is attempted. Triggers: commit --no-verify, git commit -n, git push --no-verify.

Explore ideas before implementation, design features, make architecture decisions, and validate approaches. Use when: brainstorm, explore options, design, what approach, how should we, ideas, before building.

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines.

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

Shared vocabulary for designing deep modules. Use when: design a module interface, decide where a seam goes, make code more testable, reduce coupling, evaluate if a module is too shallow, or another skill needs the deep-module vocabulary.

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Project inspection and deployment preparation workflow for staging/production. Use when: prepare deploy, deploy project, release version, check deploy.

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Build and sharpen a project's shared language (glossary) in CONTEXT.md. Use when: terms are ambiguous, the same concept has multiple names, naming a new module/concept, onboarding to a fuzzy domain, or output is too verbose because no shared vocabulary exists.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

Edit files, modify source code, fix bugs, refactor, and apply precise code changes safely. Use when: edit file, fix this, modify, replace, update code, apply changes.

Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.

Compact the current conversation into a handoff document so a fresh agent or next session can continue. Use when: hand off, end of session, context getting full, switch agents, pause work, write a handoff.

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".

Scan a codebase for deepening opportunities — refactors that turn shallow modules into deep ones — and present ranked candidates. Use when: architecture review, codebase feels like a ball of mud, too many small modules, hard to test, reduce coupling, improve maintainability.

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.

Dynamically enable, disable, and suggest MCP servers based on task needs. Use when: install MCP, add tool, enable browser, playwright, web search, database access, github MCP, suggest tools.

Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.

Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.

Guard destructive operations. Use when: delete, rm, remove, drop, truncate, credentials, config change, bulk edit.

Plan mode: write an actionable markdown plan to .kilo/plans/, no execution. Bite-sized tasks, exact paths, complete code.

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks.

Pre-commit review: security scan, quality gates, auto-fix.

Investigate a question against high-trust primary sources and capture the findings as a cited Markdown file. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background sub-agent.

Resolve in-progress git merge or rebase conflicts systematically. Use when you hit conflicts during merge, rebase, or cherry-pick.

Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.

Prepares production launches. Use when preparing to deploy to production.

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Deploy, configure, and maintain the Solo-Code multi-agent harness across Copilot, Claude, Gemini, and Kilo. Use when: deploy harness, setup copilot, setup claude, setup gemini, setup kilo, configure AI agents, install AI harness, solo-code setup, initialize project.

Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet.

Throwaway experiments to validate an idea before build.

Execute plans via task subagents (2-stage review).