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 Cratis/AI --skill cratis-screenplay-specificationsgit clone --depth 1 https://github.com/Cratis/AIWrote 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/cratis/ai/cratis-screenplay-specifications)<a href="https://agentmods.dev/skills/cratis/ai/cratis-screenplay-specifications"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-screenplay-specifications/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/cratis/ai/cratis-screenplay-specifications"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-screenplay-specifications.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 | $0.00117 | $0.04137 |
| Opus 5.5 | $0.00047 | $0.01655 |
| Sonnet 5.5 | $0.00023 | $0.00827 |
| Haiku 4.5 | $0.00012 | $0.00414 |
Grade A, and why
cratis-screenplay-specifications 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 2d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenplay specifications
Read preferred syntax when writing or reviewing .play.
A specification is the acceptance criterion for a slice, written in the same
document as the behavior it pins. Given/when/then, in business language, with
concrete data.
Locate the model
Look first for the project's existing .play files: their folder is the model.
For a new model, check Source/ or src/, else use Screenplay/ at the repository
root. Never put a model under .cratis/ or hand-copy it between repositories.
cratis ai install manages .cratis/ai/, never model files. Keep explanatory
Markdown in project documentation; .play is the single flow model.
Product sources
Specification syntax follows Screenplay Documentation/screenplay/specifications.md.
Tool versions: cratis-screenplay-toolchain SKILL.md. Compile commands check source, not
reference execution. Use screenplay test or MCP run-specifications for V4; Stage/target
tests are separate evidence. Propose → review → run-specifications with proposalId → apply.
PLAY0285 (an impossible then) unbinds the whole model and blocks every spec.
Unsupported/unbound is never a pass. Typed examples and
route assertions are in examples and routes.
Requires Screenplay 4.145.0 or later (screenplay --version) for run-specifications with proposalId.
Read source notes for the retained inline-fact and action-syntax evidence; run the changed examples at the standalone pin.
Reference execution — what actually runs
Screenplay's reference runner executes specifications against an immutable in-memory world: no Arc, no Chronicle, no database, no network. Every downstream target has one normalized behavior to match.
Binding is not plan admission. Read model-authoring's language reference when distinguishing executable declarations, refused projection shapes and opaque code. Reached opaque code is unsupported, never passed; portable denial may still execute before it. An unadmitted projection makes unsupported only the specifications that reach it (Screenplay 4.213.2 or later); other unsupported declarative constructs block the whole plan.
What ships with it
15 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.
- LICENSE 142 B
- references/actions-beyond-commands.md 2.8 KB
- references/child-ordering.md 4.7 KB
- references/concept-rules.md 3.4 KB
- references/examples-and-routes.md 11 KB
- references/generated-fixtures.md 7.7 KB
- references/outcome-comparison.md 2.4 KB
- references/persona-callers-and-cases.md 5.1 KB
- references/query-rejections.md 2.1 KB
- references/reactions-and-cascades.md 4.2 KB
- references/source-notes.md 1.5 KB
- references/vocabulary.md 5.1 KB
- references/whitespace-rules.md 4.4 KB
- references/worked-example.md 4.2 KB
- verification.json 3.7 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.
- 2d ago Changed · +4 lines 3d8a1a8e5a28
- 3d ago Changed f25fcaed9e88
- 5d ago Changed · +23 lines 4c87e4343ef3
- 6d ago Changed · +8 lines 1e5fdf601dcb
- 7d ago Changed · -47 lines 6f3a244ea33a
- 9d ago Changed · -8 lines 4ba386991bcf
- 10d ago Changed · +4 lines 03561eec900e
- 11d ago Changed · +25 lines 855125ca58b0
- 12d ago Changed · -308 lines 840b01388483
- 15d ago First seen · 583 lines · 117 tokens per session scan A 64b813679a11
cratis-screenplay-specifications is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 4,137 once invoked, about $0.0005 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 2026-09-19.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…