Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.
JavaScript agentic-codingai-agentsai-governanceautonomous-agentsclaude-codeclicode-reviewcodexcoding-agentsdeveloper-toolsgit-hooksllmlocal-firstmulti-agentsoftware-factoryspec-driven-developmentverificationvibe-coding
/** The pullboard skills command, in its own module so an item adding another command never edits these lines. */
import {
Refused,
} from '../refused.js';
import {
updateSkills,
} from '../skills.js';
import {
context,
} from '../cli.js';
/** Run `pullboard skills` and return its exit code. */
export function run(io, { first, second, rest, values }) {
if (first || second || rest.length || !values.update) throw new Refused('USAGE', 'pullboard skills --update');
const ctx = context(io);
const result = updateSkills(ctx.info.root);
io.result?.(result);
if (result.updated.length) io.say(`updated Claude Code skills: ${result.updated.map((file) => file.split('/')[2]).join(', ')}`);
else io.say('Claude Code skills are current or customized; no files were replaced');
for (const item of result.customized) {
const change = item.missing.length ? `; missing changes: ${item.missing.join('; ')}` : '';
io.say(`kept customized skill ${item.path}${change}`);
}
return 0;
}