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 skills add HermeticOrmus/claude-code-game-development --skill verify-claude-code-game-developmentgit clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-developmentWrote 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/skills/hermeticormus/claude-code-game-development/verify-claude-code-game-development)<a href="https://agentmods.dev/skills/hermeticormus/claude-code-game-development/verify-claude-code-game-development"><img src="https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/verify-claude-code-game-development/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/skills/hermeticormus/claude-code-game-development/verify-claude-code-game-development"><img src="https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/verify-claude-code-game-development.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 | $0.00087 | $0.01497 |
| Opus 5.5 | $0.00035 | $0.00599 |
| Sonnet 5.5 | $0.00017 | $0.00299 |
| Haiku 4.5 | $0.00009 | $0.00150 |
Grade A, and why
verify-claude-code-game-development 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify claude-code-game-development
claude-code-game-development is a plugin library, not a running app: 87 plugins under plugins/, published as the claude-code-game-development marketplace. Its user surface is the install. A user adds this repo as a plugin marketplace in Claude Code or Grok Build, installs plugins from it (or runs ./setup.sh from a clone), and then uses the skills, commands, agents and hooks those plugins bring. This skill drives that path in throwaway configs, so a proof never touches your own Claude Code config or Grok home.
Helper (executable, bash; needs claude, grok, jq and git): .grok/skills/verify-claude-code-game-development/bin/control-claude-code-game-development
B=.grok/skills/verify-claude-code-game-development/bin/control-claude-code-game-development
$B --help
$B doctor # worth driving? CLIs, head, manifests in sync
$B run # every plugins, both CLIs, prove each loaded; one JSON result
$B run --only godot-development # the same for the plugins a change touched
$B run --pr 12 --expect <sha> # the same on a PR head, fetched into a scratch clone
$B install --claude --only godot-development # a fresh run that keeps its clean config for the next steps
$B details godot-development # component inventory in the latest run (both CLIs)
$B setup --list # ./setup.sh inside the latest run's clean configs
$B check # scripts/check.sh, the repo's one check command
$B cleanup # drop every run's scratch; the evidence stays
JSON on stdout, progress on stderr, exit 1 on any failed proof. Everything the helper writes lives under VERIFY_CLAUDE_CODE_GAME_DEVELOPMENT_HOME (default ~/.local/share/verify-claude-code-game-development): runs/<stamp>-<head8>/ (or <stamp>-pr<N>-<head8>) holds scratch/ and evidence/, and runs/latest points at the newest run.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 76 lines · 87 tokens per session scan A 6184c378aab4
verify-claude-code-game-development is a skill published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 87 tokens to every session and 1,497 once invoked, about $0.0003 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 2026-10-05.
Other skills, from other repositories
cgs-vertical-slice
Use for vertical slice tasks that validate whether a full game loop can be built at representative quality before production commitment; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-adopt
Use for adopt tasks that inventory existing source, assets, docs, and tests before mapping work into CGS structure; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-architecture-review
Use for architecture review tasks that review architecture for layer violations, scalability risks, engine misuse, testing seams, and production readiness; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-bugfix
Use for bugfix tasks that fix a bounded bug with reproduction evidence, minimal change, regression coverage, and handoff notes; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-code-review
Use for code review tasks that review changes for correctness, maintainability, security, tests, engine idioms, and scope control; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-content-audit
Use for content audit tasks that audit content coverage, duplication, tone consistency, localization needs, and production completeness; produce verification evidence, changed or proposed files, and handoff boundaries.