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 vstrapasson/rpg-marketplace/plugin install rpg-writers-roomWrote 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/vstrapasson/rpg-marketplace/rpg-critique)<a href="https://agentmods.dev/skills/vstrapasson/rpg-marketplace/rpg-critique"><img src="https://agentmods.dev/badge/skills/vstrapasson/rpg-marketplace/rpg-critique/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/vstrapasson/rpg-marketplace/rpg-critique"><img src="https://agentmods.dev/badge/skills/vstrapasson/rpg-marketplace/rpg-critique.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 | $0.00229 | $0.02972 |
| Opus 5 | $0.00114 | $0.01486 |
| Sonnet 5 | $0.00046 | $0.00594 |
| Haiku 4.5 | $0.00023 | $0.00297 |
Grade A, and why
rpg-critique 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPG Critique (the writers' room)
What this skill is for
You have built a campaign and run some of it. This skill convenes a panel of expert critics to tell you how to make it better — five deliberately different lenses reading your vault and your session transcripts, each rating against an explicit rubric, each grounding every claim in a quote you can go check.
It is a critique layer, and it is the only skill in the kit whose product is judgment rather than content. It generates nothing, writes no lore, and edits no vault note. The deliverable is a self-contained HTML report — synthesis on top, the full room underneath.
The core idea — two evaluations, two sources, two rubrics
The thing most reviews get wrong is treating a campaign as one object. It is two:
- The artifacts — the writing. Judged from the vault notes. Is this faction interesting? Does this city give a GM something to point at?
- The conducting — the running. Judged only from the session transcripts. Pacing, spotlight, railroading, whether the clues actually reached the players, whether the NPCs came alive at the table.
They are different questions with different evidence and different failure modes, and they come apart constantly: a beautiful dossier that never surfaced in play, a thin note run brilliantly. Prep quality is not conducting quality. Never review one by reading the other — if the transcripts are missing, conducting is not judged, and the report says so.
Both are first-class. A review that only reads the vault is half a review.
If you find yourself concluding that a session went well because the prep was good, stop — you have reviewed the wrong object.
It is a room, not an oracle
Five personas on similar models are not five independent judges. Measured panels of LLM evaluators lose roughly three-quarters of their nominal independence to correlated error. So this skill is built to deliver coverage, not consensus: five angles catch more than one, and the disagreements are kept rather than averaged away. Agreement raises salience, never confidence — confidence comes from independent evidence, not from a vote. The methodology footer says this plainly in the report, and it is not optional.
What ships with it
10 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.
- references/co-creation.md 7.0 KB
- references/output-template.md 5.6 KB
- references/panel-protocol.md 7.1 KB
- references/personas/o-arquiteto.md 5.4 KB
- references/personas/o-dramaturgo.md 5.9 KB
- references/personas/o-jogador.md 5.7 KB
- references/personas/o-lazy-gm.md 5.2 KB
- references/personas/o-showrunner.md 5.2 KB
- references/report-template.html 9.3 KB
- references/synthesis-model.md 6.4 KB
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 · 143 lines · 229 tokens per session scan A 4fc1969d4b78
rpg-critique is a skill published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 229 tokens to every session and 2,972 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.