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-toolchaingit 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-toolchain)<a href="https://agentmods.dev/skills/cratis/ai/cratis-screenplay-toolchain"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-screenplay-toolchain/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-toolchain"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-screenplay-toolchain.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 | $0.00163 | $0.04089 |
| Opus 5.5 | $0.00065 | $0.01636 |
| Sonnet 5.5 | $0.00033 | $0.00818 |
| Haiku 4.5 | $0.00016 | $0.00409 |
Grade A, and why
cratis-screenplay-toolchain 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 yesterday.
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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenplay toolchain
Read preferred syntax when writing or reviewing .play.
This skill owns tool selection, verdicts and admission. Modeling method lives in
cratis-screenplay-modeling-lifecycle; syntax lives in the construct skills.
Locate the model
Decide opt-in per general.md "Model first"; where cratis-screenplay-modeling-lifecycle is installed, run its scripts/model-first-status.mjs to locate the model root. A folder of .play
files is one application: always check the folder, never one file of it.
Tool versions and the contract
Read the installed versions first: screenplay --version, cratis --version, and which -a cratis
(an older copy earlier on PATH shadows a newer install). The standalone tool and the compiler
bundled in the CLI are different releases, and the bundled one can be older; a construct the
standalone tool binds may be refused or unrendered through the CLI. Capabilities that need a
minimum release carry a one-line Requires ... note in the reference that teaches them.
Search screenplay-contract.json, not its
whole contents, for exact diagnostic code, tool name or cliCommands options.
Its version is screenplay-contract.version.
Read contract exceptions when a
superseded statement needs context; exceptions do not change the contract.
Ground rules
- Never invent syntax. Copy shapes from
references/cheat-sheet.mdand the compiled examples it names, or from a compiled documentation example. Construct keywords are closed. - Check the folder, warnings as errors.
screenplay <folder> --warnaserrororcratis screenplay validate <folder> --warnings-as-errors. Warnings hide defects: PLAY0029 (a misspelt keyword or atypeinside a slice) drops a construct silently. A committedscreenplay.jsonat the model root declares the repository's gate (checks, warnings as errors, scope, open questions): run without repeating those flags (confirm with--print-gatebefore dropping--warnaserror), read it with--print-gate, and treat a refused file as "could not run" (references/verdicts.md). - Pick the compiler deliberately and name it. Standalone
screenplayfor language checks and reference specifications;cratisfor rendering and generation. Report both tool and version, rather than transferring a verdict across releases. - Know the mode (design, executable, renderable) and write from its subset.
- Capability is not correctness. The tool you ran decides what is accepted; the domain and the documented semantics decide what is correct. On conflict keep the correct model and record a tool gap; never reshape a model to silence a tool.
- Never remove
pii,secret, authorization, list queries, automations or rules to reach V3 or a render. Report the verdict as blocked with the codes. - A clean verdict proves only its own layer. "Not run" with the reason is a valid result. Specifications written or bound are never specifications passing.
- Let the tool resolve what it can. Revisions, identities and renames come from the tool, never from hand computation; discover tool, version and root once per session and reuse them until the root, the tool or a call changes. Re-resolve only when a value actually needs to change: a failed or stale call, a different model root, a changed tool, version or configuration, or an explicit override.
What ships with it
25 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 522 B
- references/automation-translate-example.md 4.5 KB
- references/cheat-sheet-example.md 12 KB
- references/cheat-sheet.md 15 KB
- references/diagnostic-arguments.md 4.6 KB
- references/diagnostics.md 43 KB
- references/executable-example.md 3.9 KB
- references/executable-subset.md 32 KB
- references/generated-responses-example.md 2.5 KB
- references/generation-checks.md 6.0 KB
- references/generation-strategies-example.md 5.0 KB
- references/language-admission.md 10 KB
- references/neighbouring-skills.md 720 B
- references/observation-comparison.md 5.0 KB
- references/pdl-example.md 8.6 KB
- references/preferred-syntax.md 5.3 KB
- references/production-routes-and-filters.md 5.0 KB
- references/renderable-subset.md 15 KB
- references/screenplay-contract-exceptions.json 1.7 KB
- references/screenplay-contract.json 1281 KB
- references/screenplay-contract.version 8 B
- references/sources-and-streams.md 6.5 KB
- references/traps.md 15 KB
- references/verdicts.md 21 KB
- verification.json 7.2 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.
- yesterday Changed · +2 lines 45eb0b478c37
- 2d ago Changed b1b2eecf0e8f
- 3d ago Changed · -14 lines 64ebfdb91389
- 5d ago Changed · +20 lines f9a003df7099
- 6d ago Changed · +5 lines 42d8d04c5581
- 7d ago Changed · -21 lines · +6 tokens per session 84106a95c5a6
- 9d ago Changed · +11 lines 3f8fbbe5ba14
- 10d ago Changed · +20 lines 38ff52371a9d
- 11d ago Changed · +9 lines 467129e5b53f
- 12d ago First seen · 192 lines · 157 tokens per session scan A 7aa48952424e
cratis-screenplay-toolchain is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 4,089 once invoked, about $0.0007 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 2026-10-07.
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…