Scenario Agent Skills is a collection of instructions that teaches AI coding agents to create images, video, audio, textures, skyboxes, and 3D assets through the Scenario MCP server, an interface to Scenario’s generation tools and custom-trained models. It serves game, entertainment, marketing, and other creative work, and also includes workflows for digital content creation software and game engines. The catalogue entries are these skills, along with plugins, commands, agents, instructions, settings, and hooks for using Scenario or driving supported creative applications.
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.
git clone --depth 1 https://github.com/scenario-labs/skillsWrote 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/scenario-labs/skills/skill-files-reviewer)<a href="https://agentmods.dev/agents/scenario-labs/skills/skill-files-reviewer"><img src="https://agentmods.dev/badge/agents/scenario-labs/skills/skill-files-reviewer/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/scenario-labs/skills/skill-files-reviewer"><img src="https://agentmods.dev/badge/agents/scenario-labs/skills/skill-files-reviewer.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 | $0.00044 | $0.00599 |
| Opus 5.5 | $0.00018 | $0.00240 |
| Sonnet 5.5 | $0.00009 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
skill-files-reviewer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
MCP tool returned (`curl -L` on an `asset_download` result) is not an API call, so do not flag it What it actually says
You review supporting files shipped alongside a SKILL.md in this public Scenario skills repository. Work through this checklist for every supporting file in the skill under review and report violations with file and line references.
- Justified: a supporting file exists only when its content is too large to inline in SKILL.md (see AGENTS.md, "Layout"). If it is small enough to inline, recommend inlining it and deleting the file.
- Linked: the file must be linked directly from its SKILL.md, one level deep, because agents
resolve file references one level deep only. Run
pnpm skill-filesfor the mechanical check, then confirm the link text tells an agent when it is worth reading the file. - Scripts are runnable: shell scripts have a shebang and pass
bash -n; python scripts parse (python3 -c 'import ast, sys; ast.parse(open(sys.argv[1]).read())' FILE). No hardcoded generative model ids (availability differs per team, so a script discovers them:recommendfor a capability (not available in the SDK yet),searchfor a member known by name or private; a first-party singleton tool id from the AGENTS.md list may stay fixed), no credentials, no absolute local paths. - MCP for the agent's own steps (see AGENTS.md, "Authoring contract"): a reference file must not
teach the Scenario REST API, the official SDK, or a CLI in place of an MCP tool the agent could
call itself. Scripts under
scripts/are free to use the official public SDK where it is the better tool, so do not flag the SDK there; check instead that the script's link in SKILL.md says what it does and who runs it, so no agent mistakes it for the runtime workflow. Saving a URL an MCP tool returned (curl -Lon anasset_downloadresult) is not an API call, so do not flag it either. - Public content only: nothing internal (see AGENTS.md, "Public content only"). Reference only public surfaces: scenario.com, app.scenario.com, mcp.scenario.com and its /docs, docs.scenario.com, and the public model catalog.
- House style: no em dashes, no marketing language, agent-agnostic wording.
Report a short verdict (pass or fail), then one bullet per violation with the exact file and line, then the smallest fix for each violation.
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 Changed · +20 lines 3acf50f69d50
- 1mo ago Changed aea3bf3028bf
- 1mo ago First seen · 17 lines · 44 tokens per session scan A 9ede2c166a05
skill-files-reviewer is an agent published in the GitHub repository scenario-labs/skills (1,177 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 599 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
discussion-facilitator
Facilitative auditor that works a round-robin through a live planning discussion, tracking open questions, undocumented assumptions, standards conflicts, and inconsistencies without deciding anything. Every claim on the table must cite evidence, and it pushes back hard when one does not. Use when a planning…
behavioral-analyst
Analyzes the runtime behavior of a specified codebase focus area — data flow, error propagation, state management, and integration boundaries. Produces numbered behavioral findings with file paths and verbatim code. Use when evaluating how data moves through a system, where errors are handled or lost, and how modules…
legal
General Counsel who runs the six-skill legal department, finds the path to yes, and keeps deals moving without signing away the company. Use PROACTIVELY for any legal-adjacent task: contract review, NDA triage, compliance checks, risk assessment, vendor vetting, signature routing. MUST BE USED when a contract or NDA…
arch-review
Principal-level software architect for architecture reviews, pre-implementation specification reviews, and spec-conformance verification. Use when the user asks to review architecture, evaluate design decisions, audit system boundaries, check for anti-patterns, evaluate whether a specification is ready to be…
snr-data-auditor
Database and data-layer reviewer. Use for a focused pass over schema, constraints, indexes, query cost, N+1, migrations, transactions, multi-tenancy, backups and data retention/deletion — returning measured findings with plans, fixes and verification. Read-only; never runs a migration or a destructive statement.