awesome-jev plugin
A plugin with a catalogue of public Jev examples: a skill and an MCP server show how others solved the same decision task.
- 602 ★ on the repository
- Last commit
Minimal access
Why this level
- The catalogue only reads data but points to third-party code that needs review before running.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/awesome-jevDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The catalogue only reads data but points to third-party code that needs review before running.
This is third-party code. Review the repository files before installing.
What it does
The Claude Code plugin installs the `awesome-jev` skill and an MCP server over a catalogue of public projects that use Jev, TypeSafe AI's decision model. Entries are grouped by decision type: tool selection, safety gates, context compaction. Each example names the file where the usage was read, plus caveat flags. The skill also explains how the model string and request fields differ across Vercel, Cloudflare, OpenRouter and LiteLLM, and which published measurements are independent.
Who it is for. Developers wiring Jev into an agent who want worked decision examples rather than vendor documentation alone.
Good fit when
- An agent picks a tool and you want to see how other Jev projects handle it.
- Before copying someone's project you want its caveat flags.
- A model string will not resolve and you need to know if it exists on your gateway.
- You want independent or negative measurements instead of promotional figures.
Not a fit when
- You need the Jev API contract: TypeSafe ships its own `typesafe-ai` skill and docs.
- The project has nothing to do with Jev.
- Catalogue code would be run without review.
Example request
Show public examples where Jev decides whether an agent needs compacted context, and mark which were independently verified.Limitations
The catalogue covers other people's work and the repository has not tested those projects. Counts describe saved records, not current link availability or passed tests. Many entry summaries come from the projects' own descriptions. The repository license is not recognised by an identifier, so read LICENSE before reuse. Models and strings named in the catalogue can go stale: check them against provider documentation.
How to disable. Run `/plugin uninstall awesome-jev@awesome-jev` and, if needed, remove the marketplace with `/plugin marketplace remove`.
FAQ
What does the plugin install?
The `awesome-jev` skill and an MCP server. The server answers catalogue queries, and caveat flags and data freshness travel with every result.
Does it replace TypeSafe documentation?
No. For the API contract and question design the docs and the `typesafe-ai` skill are authoritative; this plugin shows what other projects did.
What is the launch board?
A page where Jev project authors post launches and vote. The data is also reachable through the MCP tools `launch_board` and `top_launches`.
Can the example code be trusted?
It is third-party and untested by the repository. Read the flags and the source before running it.
What license covers the repository?
A license is present but GitHub does not recognise its identifier. Read LICENSE for terms.
Discussion
No questions or reviews yet.
Related
PluginsA plugin and MCP server that hand no-text decisions to the Jev model and gate shell commands while the LLM writes content
Jev-Style runs small decision models on your machine: a probability per option, six skills, MCP and a Claude Code guard hook
An MCP and ACP adapter for the TypeSafe Jev decision model: typed answers and confidence gates for clicks and tool calls.
The Jev classifier as an agent tool: labels items, answers yes or no and ranks candidates with probabilities within milliseconds.
An MCP server giving an agent three Jev tools: typed yes or no, choice and score questions with probabilities, offline by default.
Five skills for the Jev model: sorting records, source checks, rubric scoring and choosing an agent's next action.
README in short
The README lays out the catalogue by decision pattern and resource kind, the vetting rules and machine-readable data for agents.