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.
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/nds-test)<a href="https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/nds-test"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/nds-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/nds-test"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/nds-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.01816 |
| Opus 5.5 | $0.00000 | $0.00726 |
| Sonnet 5.5 | $0.00000 | $0.00363 |
| Haiku 4.5 | $0.00000 | $0.00182 |
Grade A, and why
nds-test scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nds-test -- NDS Emulator Test Runner for HGSS KantoReborn
MANDATORY FIRST STEP
Read the knowledge base BEFORE any MCP tool call:
Read file: C:\dev\desmume-mcp-server\docs\HGSS_KNOWLEDGE.md
This contains verified memory addresses, frame budgets, touch blacklist, and known limitations. Every claim in that file is verified against ROM source and E2E tests.
6 ANTI-HALLUCINATION RULES
- ALWAYS call
nds_detect_statebefore any action -- never assume the game state - NEVER guess touch coordinates -- only use coordinates from HGSS_KNOWLEDGE.md
- NEVER navigate the intro manually -- always use
hgss_new_game_to_overworld - PREFER memory reads over screenshots --
hgss_verify_flags,nds_read_memoryare faster and more reliable - USE structured test plans for repeatable scenarios --
nds_run_builtin_testornds_run_test - SAVE STATE before risky actions --
nds_save_statebefore battles or transitions
TOOL HIERARCHY (prefer higher-level tools)
| Priority | Tool | When to Use |
|---|---|---|
| 1 (best) | nds_run_builtin_test |
Run a named test suite: boot, new_game_intro, flag_readwrite, full_kanto, full_kanto_real |
| 2 | nds_run_test |
Run a custom JSON test plan |
| 3 | hgss_run_recipe |
Run a named battle recipe (BROCK, MISTY, etc.) -- handles full lifecycle |
| 3 | hgss_real_battle |
State-aware battle with BATTLE detection + win_flag reading |
| 3 | hgss_new_game_to_overworld |
Start fresh game and reach overworld (story_state >= 3) |
| 3 | hgss_advance_dialogue |
Press A through dialogue until script ends |
| 3 | hgss_walk |
Walk N steps in a direction (requires OVERWORLD state) |
| 3 | hgss_interact |
Press A to interact with NPC/object (requires OVERWORLD) |
| 3 | hgss_battle_spam |
A-spam through a battle (any state, frame-count timeout, legacy) |
| 3 | hgss_battle_with_verify |
Composite: buff -> walk -> battle -> verify (supports real_battle mode) |
| 3 | hgss_buff_party |
Discover party, inject 999 stats for automated battle testing |
| 3 | hgss_verify_flags |
Batch flag verification (returns PASS/FAIL per flag) |
| 3 | hgss_read_map_id |
Read current map ID via FieldSystem discovery |
| 3 | hgss_read_location |
Read full Location (mapId, x, y, direction) |
| 3 | hgss_save_checkpoint / hgss_load_checkpoint |
Named save states for test checkpoints |
| 4 | nds_detect_state |
Check current game state (OVERWORLD, DIALOGUE, BATTLE, PRE_INIT) |
| 5 (last) | nds_press_button, nds_advance_frames, nds_touch_screen |
Raw inputs -- LAST RESORT only |
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.
- 1mo ago First seen · 140 lines · 0 tokens per session scan A 0aae40f1f945
nds-test is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,816 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
unity-test
Writes missing tests and runs them via MCP. Identifies untested code, creates EditMode/PlayMode tests, executes via runtests, reports results.
implement
Execute tasks from a track's implementation plan following TDD workflow.
test-gate
Deterministic deploy-gate — verify a staging→main bundle's acceptance criteria against running code before deploy.
qa-sweep
Full platform QA sweep — auto-discovers every page, tests every UI element via browser automation, creates GitHub issues for all findings.
backprop
Trace a bug back to a spec gap and generate regression tests.
dev-tdd
Implements a feature by following the TDD (Test-Driven Development) cycle.