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 rondorkerin/gamestack/plugin install gamestackWrote 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/rondorkerin/gamestack/procgen-review)<a href="https://agentmods.dev/skills/rondorkerin/gamestack/procgen-review"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/procgen-review/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/rondorkerin/gamestack/procgen-review"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/procgen-review.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 | $0.00169 | $0.00862 |
| Opus 5 | $0.00084 | $0.00431 |
| Sonnet 5 | $0.00034 | $0.00172 |
| Haiku 4.5 | $0.00017 | $0.00086 |
Grade A, and why
procgen-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Procgen Review
Preamble (auto-loaded)
!cat "${CLAUDE_PLUGIN_ROOT}/shared/PREAMBLE.md"; echo; cat "${CLAUDE_PLUGIN_ROOT}/ETHOS.md"
FALLBACK: if the line above rendered literally or empty (
disableSkillShellExecution), Read${CLAUDE_PLUGIN_ROOT}/shared/PREAMBLE.mdand${CLAUDE_PLUGIN_ROOT}/ETHOS.mdnow and follow PREAMBLE.md as instructions, then continue.
The quality gate for generated content. Generation is cheap and confident; sameness is invisible from inside a single sample. This skill is the review pass that catches it — designed to run automatically in a headless generate-review-repair loop (see ${CLAUDE_PLUGIN_ROOT}/shared/GATE.md for the loop harness).
When to use this
- After any batch of content is generated, before it's committed to the game
- As the standing gate inside a headless authoring loop
- To audit existing generated content for the failure modes a generator can't self-detect
What it needs
- The batch of generated artifacts (ideally ≥8 instances of a type, so sameness is detectable)
- The generator's constraint set / definition of "good" (from
procedural-generation) - Access to prior committed instances of the same type (for the sameness scan)
What it produces
A structured verdict per REVIEW.md's format: each artifact gets PASS / SOFT-FAIL / HARD-FAIL across five gates, with specific, actionable fixes routed to the phase that owns them (per game-design-process Phase 5).
Headless contract (for the GATE.md loop): emit the machine-readable verdict as the final fenced ```json block of your output, shape { "pass": bool, "score": number, "failures": [{ "gate", "detail" }] }. pass is false if any artifact HARD-FAILs. The harness extracts the last fenced json block — nothing else needs to be parseable.
The procedure
Read REVIEW.md for the full step-by-step. The five gates, in order:
- Oatmeal test — perceptual, not mathematical, uniqueness.
- Fanfic/retell test — would a player retell it?
- Cross-instance sameness scan — structural & thematic duplication vs. prior instances.
- Intentionality gate — who built it, what happened here, why this reward, completion arc.
- Anti-pattern gate — the named failure modes.
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.
- 10d ago First seen · 51 lines · 169 tokens per session scan A cc714eccff31
procgen-review is a skill published in the GitHub repository rondorkerin/gamestack (28 stars, last pushed 2mo ago), licensed MIT. It adds 169 tokens to every session and 862 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
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-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.
prototype
Concept prototype — validate the core idea is worth designing before writing GDDs. Run right after /brainstorm and /setup-engine. Routes to HTML, Engine, or Paper path based on game type. Produces a throwaway build and a PROCEED/PIVOT/KILL verdict.
dev-story
Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before…
smoke-check
Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.
test-helpers
Generate engine-specific test helper libraries for the project's test suite. Reads existing test patterns and produces tests/helpers/ with assertion utilities, factory functions, and mock objects tailored to the project's systems. Reduces boilerplate in new test files.