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-stage-rendering-and-sandboxgit 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-stage-rendering-and-sandbox)<a href="https://agentmods.dev/skills/cratis/ai/cratis-stage-rendering-and-sandbox"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-stage-rendering-and-sandbox/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-stage-rendering-and-sandbox"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-stage-rendering-and-sandbox.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 | $0.00043 | $0.04170 |
| Opus 5.5 | $0.00017 | $0.01668 |
| Sonnet 5.5 | $0.00009 | $0.00834 |
| Haiku 4.5 | $0.00004 | $0.00417 |
Grade A, and why
cratis-stage-rendering-and-sandbox 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What Stage renders, and what it refuses
Stage turns a Screenplay .play model into a Cratis Arc + Chronicle application. It
ships a renderer (a .NET library, driven from a terminal by cratis render), a
disposable sandbox container (cratis/stage, started by cratis run) and a
specification runner container (cratis/stage-specrunner).
A model Stage cannot render exactly produces no artifacts, never thinner ones. Probe the model; admission rules are not a render result.
Requires cratis CLI ≥ 3.57 (cratis --version) to render ESM v14 and v15 models; an older CLI refuses newer ESM versions with CLI-RENDER-004 (or STAGE-ESM-016 from Stage directly).
Requires Cratis CLI 3.74.0 to render ESM v21–v26 models, 3.75.0 for v27, 3.81.0 for v28 and 3.86.0 for v29–v30. CLI 3.66.0–3.73.0 refuse v21 and later with CLI-RENDER-004. Above a CLI's ceiling, a construct its bundled compiler cannot bind reports PLAY0268 before CLI-RENDER-004 is reached.
Batches, described handlers, text rules and protected reads
Start with current target boundaries, reviewed
against Stage v4.197.0: matched language/ESM 1.0–30.0 and 32.0 are admitted, not
31.0. The reviewed CLI's cratis render admits ESM through v30; its bundled
Stage then applies matched-pair and construct gates. V32 needs a direct caller of
the reviewed Stage baseline. See CLI bundle details.
Renderer, semantic Host/specification execution and legacy syntax admission are
separate gates.
Bounded atomic batches render; unverifiable query performers can produce explicit
gaps, not completed behavior. Described handlers still refuse even in Stub mode.
Keep protection and report remaining refusals.
When to use
- Deciding whether a model can be rendered, or reading a blocked render.
- Re-rendering safely after the model or a managed file changed.
- Checking what the generated UI does and does not prove.
- Running the sandbox or the specification runner, or a behavior walk.
What ships with it
14 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/admission.md 37 KB
- references/behavior-walk.md 4.5 KB
- references/case-tables-and-whole-numbers.md 4.2 KB
- references/choosing-generation.md 3.1 KB
- references/current-boundaries.md 7.4 KB
- references/date-comparisons.md 2.4 KB
- references/neighbouring-skills.md 788 B
- references/publication-and-recovery.md 1.6 KB
- references/render-example.md 6.9 KB
- references/rendered-application.md 14 KB
- references/sandbox-and-specrunner.md 18 KB
- references/scene-runtime.md 4.7 KB
- verification.json 6.3 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 · +1 lines 8aa48d21e04a
- 4d ago Changed · +6 lines 06944cc0ff2b
- 8d ago Changed 6d0542b14f83
- 10d ago Changed · -168 tokens per session fe04b5e16dc5
- 11d ago Changed · +9 lines 2c2d2ce0b4c4
- 19d ago Changed · -9 lines d612b19fc218
- 20d ago Changed · +12 lines f19c5d045028
- 21d ago Changed · +4 lines ee81bbea3c25
- 23d ago Changed · -57 lines · -4 tokens per session 8e3b1c9f7d04
- 24d ago First seen · 295 lines · 215 tokens per session scan A a419a343b703
cratis-stage-rendering-and-sandbox is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 4,170 once invoked, about $0.0002 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 2026-09-06.
cratis-stage-rendering-and-sandbox compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cratis-stage-rendering-and-sandboxCratis/AI | Skill | 4 | yesterday | MIT | A | 43 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |