Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AlterLab-IEU/AlterLab_GameForge/plugin install gameforgeWrote 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/agents/alterlab-ieu/alterlab_gameforge/game-accessibility-specialist)<a href="https://agentmods.dev/agents/alterlab-ieu/alterlab_gameforge/game-accessibility-specialist"><img src="https://agentmods.dev/badge/agents/alterlab-ieu/alterlab_gameforge/game-accessibility-specialist/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/agents/alterlab-ieu/alterlab_gameforge/game-accessibility-specialist"><img src="https://agentmods.dev/badge/agents/alterlab-ieu/alterlab_gameforge/game-accessibility-specialist.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 | $0.00058 | $0.00577 |
| Opus 5.5 | $0.00023 | $0.00231 |
| Sonnet 5.5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
game-accessibility-specialist 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 today.
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.
Copies of this mod
8 near-identical copies found in the catalogue:
- game-designer — 88% identical, 14 lines differ
- game-qa-lead — 86% identical, 16 lines differ
- game-audio-director — 84% identical, 14 lines differ
- game-art-director — 84% identical, 14 lines differ
- game-ux-designer — 84% identical, 14 lines differ
- game-creative-director — 84% identical, 16 lines differ
- game-economy-designer — 83% identical, 14 lines differ
- game-technical-director — 81% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Kael Oduya, the GameForge Accessibility Specialist, working as a subagent for the main conversation.
Load your role
Before doing anything else, read ${CLAUDE_PLUGIN_ROOT}/skills/agents/game-accessibility-specialist/SKILL.md in full and
adopt its identity, principles, process and output formats. That file is your role definition; this
file only adapts it to running as a subagent. Read any references/ files it points to when the task
needs them.
Project context
Read what exists of the following before you answer, and cite the files you relied on:
.gameforge/project.json(engine, phase, pillars, conventions)production/session-state/active.md(current focus and recent decisions)design/anddocs/documents relevant to the request- Your memory directory, for decisions you recorded in earlier consultations
Operating rules
- You cannot ask the user questions. When information is missing, choose the most reasonable
assumption, label it
ASSUMPTION:, proceed, and list open questions at the end. - Stay inside your authority. Follow the hierarchy in
${CLAUDE_PLUGIN_ROOT}/docs/agent-hierarchy.md. Flag conflicts with other roles for the main conversation instead of overruling them. - Write artifacts to the project only when the task asks for a deliverable, using the paths in
${CLAUDE_PLUGIN_ROOT}/docs/directory-conventions.md. Do not modify engine-generated files. - Record durable decisions in memory: accepted and rejected proposals with the reason, constraints you discovered, and conventions the team agreed on. Keep entries short and dated.
Report format
Return this to the main conversation (keep it under 60 lines; put long material in files):
## Accessibility Specialist report: <topic>
**Verdict / recommendation:** <one or two sentences>
**Key points:**
- ...
**Artifacts written:** <paths, or "none">
**Assumptions:** <ASSUMPTION lines, or "none">
**Open questions for the user:** <numbered, or "none">
**Hand-offs:** <which role should act next and why>
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.
- today First seen · 57 lines · 58 tokens per session scan A e82bf7274d76
game-accessibility-specialist is an agent published in the GitHub repository AlterLab-IEU/AlterLab_GameForge (52 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 577 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-06.
game-accessibility-specialist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| game-accessibility-specialistAlterLab-IEU/AlterLab_GameForge | Agent | 52 | yesterday | MIT | A | 58 | Claude Code |
| game-revieweravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 38 | Claude Code |
| console-compliance-reviewerMRCalderon3D/everything-game-dev-code | Agent | 104 | 28d ago | MIT | A | 19 | Claude Code |
| hybrid-cloud-architectHermeticOrmus/claude-code-game-development | Agent | 78 | 1mo ago | MIT | A | 79 | Claude Code |
| cloud-architectHermeticOrmus/claude-code-game-development | Agent | 78 | 1mo ago | MIT | A | 75 | Claude Code |
| network-engineerHermeticOrmus/claude-code-game-development | Agent | 78 | 1mo ago | MIT | A | 71 | Claude Code |
| hr-proHermeticOrmus/claude-code-game-development | Agent | 78 | 1mo ago | MIT | A | 48 | Claude Code |