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-ai-fullgit 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.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 | $0.01046 |
| Opus 5 | $0.00000 | $0.00523 |
| Sonnet 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 4d 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.
- 4d 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 3d 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.