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/gba-test)<a href="https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/gba-test"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/gba-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/gba-test"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/gba-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 | $0.00959 |
| Opus 5.5 | $0.00000 | $0.00384 |
| Sonnet 5.5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
gba-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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gba-test — Universal GBA Integration Test Runner
$ARGUMENTS: test mode — game profile defines available modes (e.g., smoke, gameplay, save, stress, full, ai, battle, nav, custom <description>)
5 ABSOLUTE RULES (NEVER VIOLATE)
- VERIFY state before every action (screenshot + frame check)
- Use ONLY named RECIPES from the game's guide — never invent button sequences
- Frame advances >30 require a state check before next action
- Screenshot every 5 tool calls
- If assertion fails → STOP, report failure + actual state, never retry blindly
Step 1: Detect Game
gba_get_frame— if fails, stop and report "emulator not connected"- Read ROM title:
gba_read_memory(0x080000A0, 12)— decode as ASCII - Match title against known profiles:
| ROM Title Contains | Profile |
|---|---|
POKEMON EMER or POKEMON FIRE |
profiles/pokemon-embergold.md |
BRAINATTIC |
profiles/brain-attic.md |
- If no match: run Generic Boot Test only (see below), then stop
Step 2: Load Profile
- Read the matched profile file from
~/.claude/commands/profiles/ - Read the game's guide file (path specified in profile) completely — MANDATORY before any further MCP calls
- Note the profile's available test modes and recipes
Step 2.5: Johto Mode Prerequisites
If the requested mode starts with johto-:
- Check which save state slots exist by attempting
gba_load_state(N)for slots 2-8:- If slot loads without error and
pokemon_get_mapreturns group=43 → slot is valid Johto checkpoint - Track which slots are available vs missing
- If slot loads without error and
- Report available vs required slots
- If zero Johto save states exist (none of slots 2-8 are valid), STOP and report:
Johto test modes require save states at story checkpoints. Play through the game and save at each checkpoint per the guide (section 9). Required slots: 2 (New Bark) through 8 (Blackthorn City). - If some slots exist, proceed with available checkpoints only. Report which phases will be skipped due to missing slots.
- Reload a known-good state before continuing:
gba_load_state(1)to restore Kanto baseline.
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 · 87 lines · 0 tokens per session scan A 73f7ac202adc
gba-test is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 959 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
qa-sweep
Full platform QA sweep — auto-discovers every page, tests every UI element via browser automation, creates GitHub issues for all findings.
qa-automation
Set up a comprehensive test automation strategy.
qa-e2e
End-to-End tests with Playwright or Cypress.
tester
Comprehensive testing with parallel execution capabilities.
e2e
Generate and run E2E tests with Playwright.
test-browser
Run browser tests on pages affected by current PR or branch.