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 agentmods add skills/wibus-wee/cradle-app/elysiajsnpx skills add wibus-wee/cradle-app --skill elysiajsgit clone --depth 1 https://github.com/wibus-wee/cradle-appWhat 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 | $0.00020 | $0.03479 |
| Opus 5 | $0.00010 | $0.01740 |
| Sonnet 5 | $0.00004 | $0.00696 |
| Haiku 4.5 | $0.00002 | $0.00348 |
Grade A, and why
elysiajs 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
52 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.
- examples/basic.ts 168 B runs code
- examples/body-parser.ts 714 B runs code
- examples/complex.ts 2.5 KB runs code
- examples/cookie.ts 751 B runs code
- examples/error.ts 654 B runs code
- examples/file.ts 216 B runs code
- examples/guard.ts 682 B runs code
- examples/map-response.ts 299 B runs code
- examples/redirect.ts 136 B runs code
- examples/rename.ts 818 B runs code
- examples/schema.ts 1.1 KB runs code
- examples/state.ts 126 B runs code
- examples/upload-file.ts 343 B runs code
- examples/websocket.ts 538 B runs code
- integrations/ai-sdk.md 2.0 KB
- integrations/astro.md 1.2 KB
- integrations/better-auth.md 2.6 KB
- integrations/cloudflare-worker.md 1.8 KB
- integrations/deno.md 627 B
- integrations/drizzle.md 6.0 KB
- integrations/expo.md 1.8 KB
- integrations/nextjs.md 2.1 KB
- integrations/nodejs.md 1.0 KB
- integrations/nuxt.md 1.1 KB
- integrations/prisma.md 1.9 KB
- integrations/react-email.md 3.0 KB
- integrations/sveltekit.md 1.2 KB
- integrations/tanstack-start.md 1.8 KB
- integrations/vercel.md 935 B
- patterns/mvc.md 11 KB
- plugins/bearer.md 698 B
- plugins/cors.md 3.7 KB
- plugins/cron.md 8.6 KB
- plugins/graphql-apollo.md 1.6 KB
- plugins/graphql-yoga.md 1.7 KB
- plugins/html.md 3.8 KB
- plugins/jwt.md 6.5 KB
- plugins/openapi.md 4.2 KB
- plugins/opentelemetry.md 4.1 KB
- plugins/server-timing.md 1.8 KB
- plugins/static.md 1.8 KB
- references/bun-fullstack-dev-server.md 2.3 KB
- references/cookie.md 3.6 KB
- references/deployment.md 6.9 KB
- references/eden.md 3.5 KB
- references/lifecycle.md 5.3 KB
- references/macro.md 1.8 KB
- references/plugin.md 4.9 KB
- references/route.md 7.3 KB
- references/testing.md 8.1 KB
- references/validation.md 10.0 KB
- references/websocket.md 4.0 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 First seen · 476 lines · 20 tokens per session scan A c553412bafe0
elysiajs is a skill published in the GitHub repository wibus-wee/cradle-app (72 stars, last pushed yesterday), with no licence file. It adds 20 tokens to every session and 3,479 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
automations
Create and manage bb automations from the first-party automations plugin. Use when scheduling recurring or one-shot agent/script work with bb automation commands.
tasks
Use when asked to work on or track a task in the Tasks plugin, when the prompt mentions a task key such as ABC-12, or when work needs task comments, attachments, delegation tracking, or status updates.
skill-creator
Create new bb skills and improve existing ones. Use whenever a user asks to create, write, edit, refine, test, or optimize a skill; turn a workflow into a reusable skill; fix skill triggering; or improve a SKILL.md file.
docs
Access and update the user's Docs vaults. Use whenever the user asks to read, find, create, update, or store a note, document, plan, or HTML artifact; when a Docs @-mention appears in context; or when an answer should link to a document the user can open in Docs.
plugin-guide-maintenance
Keep the Plugin Guide aligned with public Plugin SDK changes that affect its documented contract. Use this skill when an addition, change, rename, stabilization, or removal in @get-bb/plugin-sdk, app.slots., or BbPluginApi changes a Guide card, API symbol list, fixture, or SDK inventory. Do not use it for internal API…
bb-cli
Use this when controlling bb. The bb CLI inspects and manages threads, environments, projects, machines, providers, skills, plugins, settings, terminals, and other BB services.