AI Pilot

Plugin ai-pilot in Fusengine/codex-plugins. Commands read from the repo's manifest — today.

Skills (19)

• agent-creator

  Use when creating expert agents. Generates agent.toml (model tier, sandbox_mode, developer_instructions with required sections) and wires skill references.

• apex-methodology

  Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).

• brainstorming

  Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.

• challenge

  Use before a root-cause, a done/verified claim on a consequential change, an irreversible action, or a 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate of full APEX. Not for code correctness (use sniper), nor for a trivial 1-3 line apex-quick change

• code-quality

  Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).

• elicitation

  Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).

• exploration

  Use when exploring an unfamiliar codebase -- architecture analysis, pattern detection, dependency mapping, rapid discovery.

• fuse-browser-usage

  Use when about to call any mcp__fuse-browser__* tool. Routes fetch/crawl/SERP vs live browser session vs screenshot capture, and enforces the 4 ZERO-TOLERANCE rules -- read BEFORE the tool call.

• lead-orchestration

  Coordinate lead delegation safely, from owner request to verified report: the detailed version of the AGENTS.md COORDINATOR PATH (receive, check the place is free, analyze, decompose, distribute, brief, launch, follow, verify, control, report). Use before any lead delegation, subagent, or team actio

• modularize

  Use when converting existing code to modular architecture (Laravel, Next.js, React). Triggers: \"modularize\", \"convert to modules\", \"migrate to modular\", \"restructure modules\".

• pr-summary

  Summarize current pull request with diff, comments, and changed files. Use when reviewing PRs or before merging.

• react-effects-audit

  Use when auditing React or Next.js components for unnecessary or unsafe useEffect usage -- detects 9 anti-patterns from \"You Might Not Need an Effect\".

• research

  Use when researching documentation, best practices, or complex technical investigations -- Context7 + Exa + Sequential Thinking methodology.

• skill-creator

  Use when creating new skills, restructuring existing skills, or improving skill documentation.

• sniper-check

  Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.

• tdd

  Use when writing production code that needs tests -- new features, bug fixes, refactoring. Enforces RED-GREEN-REFACTOR before implementation.

• think-in-code

  Use when analyzing multiple files, auditing a codebase, scanning dependencies, or counting lines -- one Bash pipeline beats N sequential Read calls.

• verification

  Use when marking a task complete, finishing a feature, or claiming a bug fixed -- verifies functional resolution before closing. Do NOT use for lint/quality checks (use sniper AFTER this).

• web-performance

  Use when writing or changing web app code (front, backend, DB) to apply performance defaults, or when asked to audit performance (\"audit perf\", \"why is it slow\") -- 31 rules across front, backend+DB and infra, each with status, evidence and user cost. Advisory: audits and recommends, never edits

Slash commands (12)

• /ai-pilot:apex-quick

  Quick Flow for a trivial 1-3 line change - one delegated domain expert locates, fixes, self-reviews and proves it with a real functional check; the lead verifies on disk and runs full sniper.

• /ai-pilot:apex

  APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Eliminates hallucinations, errors, and bugs to produce clean, maintainable code.

• /ai-pilot:cleanup-context

  Memory optimization - removes duplicates, consolidates knowledge, and cleans memory banks for better performance.

• /ai-pilot:create-pull-request

  Auto-generate Pull Request with comprehensive description, test plan, and changelog. Hands push and PR creation to the commit agent.

• /ai-pilot:deep-code-analysis

  Comprehensive codebase investigation using research-expert for documentation, explore-codebase for structure, and deep analysis. Perfect for understanding complex systems.

• /ai-pilot:epct

  Systematic Explore-Plan-Code-Test methodology for structured development. Ensures comprehensive approach to feature implementation.

• /ai-pilot:explain-architecture

  Analyze and explain software architecture with ASCII diagrams and pattern detection. Creates visual representations of system design.

• /ai-pilot:fix-pr-comments

  Systematically resolve Pull Request review comments using gh CLI to fetch comments and apply requested changes.

• /ai-pilot:prisma-optimize

  Optimize Prisma queries with automated analysis, N+1 detection, index recommendations, and performance patterns based on official documentation

• /ai-pilot:run-tasks

  Execute GitHub issues using full EPCT workflow (Explore-Plan-Code-Test). Converts issue requirements into completed PR.

• /ai-pilot:update-harness

  Update the shared @fusengine/harness to the latest published version — bumps the repo's package.json, reinstalls, audits all 11 scopes against the installed binary, and only then advances the HARNESS_VERSION tripwire.

• /ai-pilot:watch-ci

  Monitor CI/CD pipeline and automatically fix failures. Watches GitHub Actions runs and applies fixes when tests fail.

Hooks (11)

• UserPromptSubmit

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• SubagentStart

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• PreToolUse

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• PreToolUse

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• PreToolUse

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• SubagentStop

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• Stop

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• PostToolUse

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• PostToolUse

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• PostToolUse

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

• SessionEnd

  bun "${CODEX_HOME:-$HOME/.codex}/node_modules/@fusengine/harness/dist/cli/bin.mjs" hook codex aipilot

Similar plugins