All Claude Code modsiuliandita/mods
prompt-gate
Before the main model spends a turn on a vague prompt, a small model, checked by Jev when TYPESAFE_API_KEY is set, says so and asks one short question. Default mode dry only measures. With a key set, the prompt goes to api.typesafe.ai (Jev) from every directory unless jevPaths limits it.
prompt-gate reaches L3 (network) and passed claude plugin validate on Claude Code 2.1.312.
- Events hooked: 3
- API methods referenced: 12
- Access from classified calls: L3, network: network, drives Claude, reads files, reads env vars, persists state, draws
- Static scan, not a runtime test
Install hint
/plugin install prompt-gate --marketplace iuliandita/modsFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
L3 Uses the networknetwork, drives Claude, reads files, reads env vars, persists state, drawsValidation
Passed on Claude Code 2.1.312View the source on GitHub Back to the list
What the scan recorded
- Observed events
- every prompt
- Hooks
session.start, command.run {command=prompt-gate}, prompt.submit- API calls
$.clock.after, $.clock.now, $.clock.sleep, $.command.register, $.env.get, $.fs.read, $.http.fetch, $.model.complete, $.session.cwd, $.store.get, $.store.set, $.ui.toast- Validation on 2.1.312
- Passed
- Scanned revision
21f20e6be898- Marketplace passed
- iuliandita-mods
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. What a mod can access and how the scan works.
More from iuliandita/mods
- delegation-boardA live pane of the session's subagents and teammates: type, model, effort, state, elapsed time, tokens, an op…
- guard-rulesBlocks AI attribution in commits and PRs, direct commits to protected branches, commits under the wrong git i…
- secret-boxKeeps secret values out of the chat: write {{secret:NAME}} in a Bash command and the value is filled in at ex…
- skill-pickNames the 1 to 5 installed skills that fit each prompt, as many as the ask needs, with a small model and, whe…
- statuslineA two-row status line in the band above the prompt, in the terminal and in Claude Desktop: model and effort,…
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/iuliandita--mods--prompt-gate/)
[](https://mods.aidojo.si/mods/iuliandita--mods--prompt-gate/)