@zedtech/zedkit-ai
Run one gate command and keep a log that setup validation accepts
Run a shell command and write a gate log in the `CMD:` / `START:` / `END:` / `EXIT:<code>` shape that `zedkit-ai validate --setup` checks, with the V8 heap cap…
At a glance
- Who: Agents and maintainers who run lint, test or build gates and need the result as evidence.
- What: Run a shell command and write a gate log in the
CMD:/START:/END:/EXIT:<code>shape thatzedkit-ai validate --setupchecks, with the V8 heap capped and aCAUSE:line when the command times out, is killed or runs out of memory. - Use when: When a setup run, a handoff or a PR cites a gate and the log must outlive the chat.
- Avoid when: For interactive commands or when a CI job already stores its own log.
- See also: Check that skills, subagents, commands and provider copies are valid
Install
pnpm add @zedtech/zedkit-aiLatest: 1.0.0 (via changesets).
Example
import { runGate } from "@zedtech/zedkit-ai";
const result = await runGate({
cmd: "pnpm exec turbo run test --concurrency=2",
log: ".agents/setup-log/gates/test.log",
timeoutMs: 20 * 60_000,
});
if (!result.ok) throw result.error;
process.exitCode = result.value.code;Wraps: (none)
Check that skills, subagents, commands and provider copies are valid
Validate installed skills, subagents and commands, report drift between providers without asking to overwrite user files, and flag kit skills a provider layer…
Route an agent call to a model and effort from a policy file
Resolve kind (how the agent is used for this call) times stakes (how much is at risk) and the call's needs to a provider's model and effort, with the gates of…