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-ai-full)<a href="https://agentmods.dev/commands/intellegix/intellegix-code-agent-toolkit/gba-ai-full"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/gba-ai-full/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-ai-full"><img src="https://agentmods.dev/badge/commands/intellegix/intellegix-code-agent-toolkit/gba-ai-full.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 | $0.01046 |
| Opus 5.5 | $0.00000 | $0.00418 |
| Sonnet 5.5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
gba-ai-full 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gba-ai-full — Full AI Behavior Regression Test
MANDATORY FIRST STEP
Read docs/gba-claude-guide.md from C:\Users\AustinKidwell\ASR Dropbox\Austin Kidwell\04_ResearchAnalysis\pokefirered-master\pokefirered-master completely before any MCP tool call.
5 ABSOLUTE RULES
- VERIFY state before every action (screenshot + callback2)
- 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
Prerequisite
Save state 9 must exist (Route 1 grass, map 3/19). If not, run RECIPE 3 (bedroom → grass) first.
Test Phases
Phase 0: Setup Verification
RECIPE 2: Load state 9
ASSERT: map 3/19, position near grass
Screenshot
Phase 1: Win Battle — Loyalty & Counter Increments
gba_load_state(9)
PRE: pokemon_get_loyalty(0), pokemon_get_ai_party_data(0) → record values
RECIPE 4 → RECIPE 5 → RECIPE 6 → RECIPE 7
ASSERT: battleCount +1, victoryCount +1, loyalty increased (+2 or +3)
Phase 2: Lose Battle — Faint Counter & Loyalty Penalty
gba_load_state(9)
PRE: record loyalty, faintCount
RECIPE 8 (force loss: HP=1, speed=0)
POST: pokemon_get_ai_party_data(0)
ASSERT: faintCount +1, loyalty decreased
Phase 3: Trauma Recording
RECIPE 9 (full procedure — sets faintCount=2, clears trauma, force loss)
ASSERT: faintCount >= 3, trauma bits non-zero
Phase 4: Revenant Transformation
RECIPE 10 (full procedure — enable nightmare, clear reserved, force loss)
ASSERT: reserved byte & 0x02 != 0 (REVENANT_BIT set)
Phase 5: Type KO Counter Increment
gba_load_state(9)
Read SB2 pointer, zero all 18 typeKOCounts (SB2 + 0xB20 + 167, 18 bytes)
RECIPE 4 (trigger encounter)
Read enemy types: gba_read_memory(0x02021410 + 88 + 0x21, 1) → type1
gba_read_memory(0x02021410 + 88 + 0x22, 1) → type2
RECIPE 5 (win battle — ASSERT outcome=1)
RECIPE 6 (wait end)
Read typeKOCounts via pokemon_get_ai_config
ASSERT: typeKOCounts[enemyType1] >= 1
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 · 100 lines · 0 tokens per session scan A 8286390a376b
gba-ai-full 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 1,046 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.