aif 플러그인

Interview until user and agent share the outcome picture, preview it, then give evidence-backed advice.

Automate tool-managed browsers with agent-browser for snapshots, clicks, forms and browser testing.

Analyze and generate image, audio, video and document content, falling back from native vision to the Multix CLI and live provider catalogs.

Turn unclear intent into an accepted outcome and compare viable approaches before delivery.

Drive a real Google Chrome profile via Chrome DevTools MCP with the chrome-profile CLI, deterministic profile discovery and URL-anchor tab selection.

Review code for bugs, regressions, maintainability, reliability and verification gaps with evidence.

Debug failing or misbehaving code by proving the root cause before any fix; diagnose why something fails, gives wrong output or is flaky in CI.

Reason by the Claude Fable 5.1 protocol: grounded claims, multi-hypothesis diagnosis, self-review, Floor checks for trick questions, Constraint Loops for exact formats.

Fix bugs, test failures, type and lint errors, log errors, UI defects and CI/CD failures with intelligent routing.

Run Git staging, commits, pushes and merges with conventional commits, auto-split by type/scope, and secret scanning.

Create, validate or review implementation plans with acceptance criteria and executable phases; /aif:serve implements them.

Apply systematic techniques when stuck: complexity spirals, innovation blocks, recurring patterns, assumptions, simplification or scale.

Scout a codebase fast with native search, optional Explore agents and user-permitted OpenCode probes.

Research technical solutions, analyze architectures and gather requirements.

Implement features, plans and fixes through a structured workflow.

Ship a completed branch via tests, review, commit, push and PR, with official/beta aliases, Chef advice and gated merge plus CI convergence.

Run unit, integration, e2e and UI tests with coverage analysis, build verification, visual regression and QA reports.

Test web apps with Playwright, Vitest and k6: E2E, unit, integration, load, security, visual and a11y.

Use this agent to run the interview-driven `aif-advise` advisory workflow in an isolated context on the strongest available model. It scouts, interviews the user one question at a time until the requirements and expected outcome are locked, relays a visual preview of that outcome for the user to con

>-

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

Use this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run tests for debugging purposes, or optimize system performance. This includes troubleshooting errors, i

Use this agent to create, reconcile, or audit evidence-backed project documentation for both people and AI collaborators without imposing a fixed docs layout, while honouring an explicit route the repository or the user supplies.

Fast codebase scanner and analyzer for locating relevant files, tracing relationships, and summarizing implementation context.

Execute implementation phases from parallel plans. Handles backend (Node.js, APIs, databases), frontend (React, TypeScript), and infrastructure tasks. Designed for parallel execution with strict file ownership boundaries. Use when implementing a specific phase from `/aif-plan --parallel` output.

Stage, commit, and push code changes with conventional commits. Use when user says "commit", "push", or finishes a feature/fix.

Use this agent when you need to research, analyze, and create comprehensive implementation plans for new features, system architectures, or complex technical solutions. This agent should be invoked before starting any significant implementation work, when evaluating technical trade-offs, or when you

Use this agent when you need to quickly locate relevant files across a large codebase to complete a specific task. Use it proactively when:\n- Beginning work on a feature that spans multiple directories\n- User mentions needing to "find", "locate", or "search for" files\n- Starting a debugging sessi

Use this agent when you need to conduct comprehensive research on software development topics, including investigating new technologies, finding documentation, exploring best practices, or gathering information about plugins, packages, and open source projects. This agent excels at synthesizing info

Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or mak

Use this agent when the user needs UI/UX design work including interface designs, wireframes, design systems, user research, responsive layouts, animations, or design documentation.

Read|Write|Edit|Bash|PowerShell, Bash|PowerShell|Read

*

*

*