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/gba-smokegit 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-smoke)<a href="https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/gba-smoke"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/gba-smoke.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00696 |
| Opus 5 | $0.00000 | $0.00348 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
gba-smoke 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gba-smoke — Universal GBA Emulator Smoke Test
5 ABSOLUTE RULES
- VERIFY state before every action (screenshot + frame check)
- ONLY named RECIPES — never invent button sequences
- Frame advances >30 → state check first
- Screenshot every 5 tool calls
- Assertion fail → STOP, report, never retry blindly
Tier 1: Universal Assertions (4 tests, any ROM)
These run BEFORE game detection. If any fail, stop immediately.
gba_get_frame→ ASSERT responds with frame number > 0 (emulator running)gba_screenshot→ ASSERT visible content on screen (not black/blank)gba_advance_frames(60)→ ASSERT no error (ROM executes without crash)gba_get_frame→ ASSERT frame number increased (game loop is advancing)
Tier 2: Game-Specific Assertions
Step 1: Detect Game
Read ROM title: gba_read_memory(0x080000A0, 12) — decode as ASCII.
| ROM Title Contains | Profile | Action |
|---|---|---|
POKEMON EMER or POKEMON FIRE |
profiles/pokemon-embergold.md |
Load profile, run its smoke mode |
BRAINATTIC |
profiles/brain-attic.md |
Load profile, run its smoke mode |
| (no match) | none | Skip Tier 2, report Tier 1 only |
Step 2: Load Profile and Guide
- Read the matched profile from
~/.claude/commands/profiles/ - Read the game's guide file completely (path in profile) — MANDATORY
- Execute the profile's
smokemode test sequence
Step 3: Merge Reports
Combine Tier 1 + Tier 2 results into a single table.
Report Format
With Game Profile
| # | Tier | Test | Expected | Actual | Result |
|---|------|------|----------|--------|--------|
| 1 | T1 | Emulator responds | frame > 0 | ... | PASS/FAIL |
| 2 | T1 | Screenshot | visible screen | ... | PASS/FAIL |
| 3 | T1 | Frame advance | no error | ... | PASS/FAIL |
| 4 | T1 | Frame advancing | frame increased | ... | PASS/FAIL |
| 5+ | T2 | (game-specific) | ... | ... | PASS/FAIL |
Without Game Profile
| # | Tier | Test | Expected | Actual | Result |
|---|------|------|----------|--------|--------|
| 1 | T1 | Emulator responds | frame > 0 | ... | PASS/FAIL |
| 2 | T1 | Screenshot | visible screen | ... | PASS/FAIL |
| 3 | T1 | Frame advance | no error | ... | PASS/FAIL |
| 4 | T1 | Frame advancing | frame increased | ... | PASS/FAIL |
ROM title: <detected title> — no matching profile found. Only universal tests ran.
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.
- 3d ago First seen · 63 lines · 0 tokens per session scan A cec9daed1cc5
gba-smoke is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 696 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
playsts2
Play Slay the Spire 2 using the MCP tools (mcpsts2). Your goal is to play as well as possible and win the run.
unity-interview
Socratic interview flow — explores requirements, identifies edge cases, clarifies scope, and outputs a structured feature brief before any coding begins.
unity-learn
Review accumulated session learnings, extract recurring patterns, and draft new skills from session data.
unity-team
Parallel agent orchestration — spawns multiple specialized agents simultaneously for faster development. Supports preset teams and custom combinations.
unity-workflow
Full development pipeline — clarify requirements, plan implementation, execute with agents, verify with review + tests.
unity-doctor
Diagnostic health check — verifies MCP connectivity, .claude/ integrity, Unity project structure, and hook registration.