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 frabcd/codex-ai-game-studio --skill skill-testgit clone --depth 1 https://github.com/frabcd/codex-ai-game-studioWrote 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/frabcd/codex-ai-game-studio/skill-test)<a href="https://agentmods.dev/skills/frabcd/codex-ai-game-studio/skill-test"><img src="https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/skill-test/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/frabcd/codex-ai-game-studio/skill-test"><img src="https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/skill-test.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 | $0.00031 | $0.00526 |
| Opus 5 | $0.00015 | $0.00263 |
| Sonnet 5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
skill-test 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 7d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Port provenance: adapted from the pinned upstream source at
984023ddac0d5e27624f2baacde6105e45de375funder MIT; see the repository parity ledger for the exact path and blob.
Test a Codex skill
Evaluate a target skill as both a package and a behavior. Testing is read-only unless the user separately approves writing a report.
Static validation
- Locate the skill directory and read
SKILL.mdplusagents/openai.yaml. - Require YAML frontmatter containing exactly
nameanddescription. - Confirm the directory name and frontmatter name match and use lowercase hyphen-case.
- Confirm the description explains both what the skill does and when it should activate. Reject unsupported legacy frontmatter and broken relative links.
- Confirm
agents/openai.yamlhas a useful display name, a 25-64 character short description, and a default prompt that explicitly names the skill. - Confirm mutating setup, installation, engine-control, catalog-refresh, and destructive enhancement workflows disable implicit invocation.
- Scan for secrets, absolute developer paths, path escapes, unsupported model pins, product-specific tool declarations, and platform-only assumptions.
Run the official skill validator when it is available. Report the exact command, exit status, and diagnostics.
Forward testing
Use isolated Codex subagents with the raw skill instructions. Cover:
- a direct explicit invocation;
- a natural-language request that should select the skill when implicit use is enabled;
- a near-miss that should route elsewhere;
- a negative or unsafe request that must preserve approval and rights gates.
Do not reveal an expected answer in the test prompt. Score routing, instruction adherence, safety boundary, artifact clarity, platform neutrality, and evidence. For failures, distinguish instruction defects from missing external capabilities.
Return a concise test matrix and a prioritized improvement proposal. Do not edit the tested skill until the user approves that separate change.
What ships with it
1 file 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.
- 7d ago First seen · 50 lines · 31 tokens per session scan A 159b23706147
skill-test is a skill published in the GitHub repository frabcd/codex-ai-game-studio (10 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 526 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
test-gen
Generate and verify tests — happy path, edge cases, error paths — using the project's own framework and patterns.
game-qa
Verify a game with evidence on its selected target runtime. Launch the actual build and prove real rendering, input, the core loop, at least one designed outcome, restart, and explicit limitations without dressing subjective fun up as a certain verdict. Use for test a generated game, QA a game build, check whether the…
verify
Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown.
skill-test
Use when a contributor wants to lint a Summer skill before commit, audit the whole library, or check a behavioral spec assertion — validates against static structural rules and per-skill behavioral specs. Trigger on "skill test", "lint skill", "validate skill".