Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/intellegix/intellegix-code-agent-toolkit/nds-buildgit clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.04160 |
| Opus 5 | $0.00000 | $0.02080 |
| Sonnet 5 | $0.00000 | $0.00832 |
| Haiku 4.5 | $0.00000 | $0.00416 |
Grade B, and why
nds-build scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
All NDS testing uses these MCP tools (registered as `nds-emulator` in `~/.claude/settings.json`): How it starts
The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nds-build — Universal NDS Game Builder
Usage
/nds-build [subcommand] [args]
Subcommands
new <name> — Scaffold a new NDS project
Creates a complete project skeleton ready to compile. After scaffolding, runs /research-perplexity to plan the module breakdown for the game.
develop <description> — Research-driven modular game build
The main game development workflow. Takes a game description and builds the entire game modularly with research gates and E2E testing at every step.
build — Compile the current project
Runs make, packages with ndstool, loads ROM into DeSmuME, and takes a screenshot of both screens.
test — Run the game's test suite
Executes ALL module tests in sequence via MCP tools. Reports per-module pass/fail.
docs — Generate gameplay documentation
Auto-generates GAMEPLAY.md, TECHNICAL.md, and MCP-TOOLS.md from code.
asset <file> — Convert a graphics/audio file
Runs grit (with NDS-specific flags) or mmutil with appropriate settings.
Instructions
Step 1: Load the NDS Builder Skill
Read the nds-builder skill for complete NDS development reference. This gives you:
- Hardware register map (hardware-ref.md)
- Game architecture patterns (architecture-patterns.md)
- Asset pipeline reference (asset-pipeline.md)
- Testing framework (testing-framework.md)
- Documentation generator (docs-generator.md)
Step 2: Detect Context
Determine what's being requested from the subcommand:
If develop <description>:
This is the primary game-building workflow. It enforces research-driven decisions, modular construction, and E2E testing gates.
Phase A: Research
Run /research-perplexity with the game description to get:
- Recommended architecture (which patterns from architecture-patterns.md apply)
- Module breakdown (what to build and in what order)
- Asset requirements (sprites, tilesets, audio needed)
- NDS-specific constraints and gotchas for this genre
- Estimated VRAM/RAM budget (main engine + sub engine)
- Dual-screen layout strategy (what goes on which screen)
- Touch screen interaction design (if applicable)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 373 lines · 0 tokens per session scan B 01c092903b10
nds-build is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,160 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
apply-design-md
Consume the project's design contract — a .design file or DESIGN.md — and thread its tokens through UI code (CSS, Tailwind, or design-system components).
agentation-fix
Session-2 fix loop for Agentation — read structured annotations from the dev overlay and apply targeted UI fixes.
motion-audit
Audit animation timing, easing, springs, and transitions — decide first whether motion should exist, then apply the motion cluster.
scan-ai-tells
Scan UI or marketing copy for AI-default tells and content-authenticity misses — deletion list, not a redesign brief.
unity-workflow
Full development pipeline — clarify requirements, plan implementation, execute with agents, verify with review + tests.
unity-feature
Plans and implements a Unity feature — identifies subsystems, loads skills, writes code, sets up scene elements via MCP.