intellegix/intellegix-code-agent-toolkit

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Run a Perplexity query by typing /control in the browser — a custom Comet command that activates browser control mode with Dropbox/GitHub context. Single entry point for all Perplexity research.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Capture Perplexity session state (cookies, localStorage, model preferences) from an already-authenticated browser session. Cached data is used by /council-refine and /export-to-council to skip fragile UI model-selector clicks.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Extract a completed Perplexity Model Council response from the current browser tab, converting it to structured markdown with model attribution, and save to disk.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Submit a plan to 3 frontier AI models (GPT-5.2, Claude Sonnet 4.5, Gemini 3 Pro) via Perplexity API for iterative refinement, with Opus 4.6 extended thinking synthesis. Loop until convergence (score >= 8, no critical issues, score gain < 1) or max 3 iterations.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Run a divergent ideation pipeline to discover novel features for the current project. Unlike convergent research commands (/research-perplexity, /export-to-council), this command brainstorms new ideas the user hasn't thought of, then scores viability and generates implementation blueprints.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Ensure the current Perplexity thread is filed into a Space named after the active project. Creates the Space if it doesn't exist.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Query 3 frontier AI models (GPT-5.2, Claude Sonnet 4.5, Gemini 3 Pro) via Perplexity API or browser automation, then synthesize findings. Automatically enters plan mode to study implementation.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Runs 5–40 iterative researchquery passes against any artifact (architectural blueprint, implementation plan, debugging trace, refactor proposal, single function) and stops when iterations converge — no new findings, no new contradictions, no new options worth exploring. Produces a definitive verdict + exhaustive list…

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Analyze and fix the GitHub issue: $ARGUMENTS.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Perform a thorough live E2E test of a frontend web application using browser-bridge MCP tools. Tests every page, interactive element, form, navigation flow, responsive breakpoint, and accessibility rule through real browser interaction.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Read docs/gba-claude-guide.md from C:\Users\AustinKidwell\ASR Dropbox\Austin Kidwell\04ResearchAnalysis\pokefirered-master\pokefirered-master completely before any MCP tool call.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Composes /gba-build develop, /gba-ai-full, /research-perplexity, /creative-research, and /orchestrator-multi into a single autonomous mega-pipeline that researches, plans, parallelizes implementation, AI-playtests, iterates on failures, discovers creative features, and ships production-ready GBA games.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Command "gba-build" from intellegix/intellegix-code-agent-toolkit, covering /gba-build — universal gba game builder, usage, subcommands, new — scaffold a new gba project and develop — research-driven modular game build.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

These run BEFORE game detection. If any fail, stop immediately.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

$ARGUMENTS: test mode — game profile defines available modes (e.g., smoke, gameplay, save, stress, full, ai, battle, nav, custom ).

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Create a comprehensive handoff document for the current work session.

intellegix/intellegix-code-agent-toolkit

Command Claude Code needs its repo

Perform a comprehensive, read-only end-to-end review of any portfolio app across three layers — Frontend (E2E), Database integrity, and Audit Log & User Activity — and produce a structured, observations-only report. Optionally, on explicit opt-in, generate (never apply) the infrastructure provisions needed so future…

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Bridge the gap between creative-research blueprints and executable implementation plans. Uses 2-4 targeted Perplexity research queries to produce a dependency-aware, externally-validated plan ready for TaskCreate and /orchestrator-multi.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Implement the feature described: $ARGUMENTS.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Initialize or verify any project environment. Auto-detects first-run vs health-check mode.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Run a query using Perplexity's /labs mode via Playwright browser automation. Similar to /research-perplexity but uses Perplexity's experimental labs mode with a longer 15-minute timeout for complex queries.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Build a structure in Minecraft Bedrock by grounding the design in real-world architectural references (via Perplexity) before placing a single block.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Command "nds-build" from intellegix/intellegix-code-agent-toolkit, covering /nds-build — universal nds game builder, usage, subcommands, new — scaffold a new nds project and develop — research-driven modular game build.

intellegix/intellegix-code-agent-toolkit

Command Claude Code

Read the knowledge base BEFORE any MCP tool call.