YeonGyu-Kim
8c6e8e4986
Fully rename the ultragoal component to ulw-loop so the identifier matches the ulw-loop skill it powers. Renames the component directory, nested skill, TS identifiers (UlwLoop / ULW_LOOP_* / ulwLoop*), the omo ulw-loop CLI subcommand, the .omo/ulw-loop state directory, the OMO_ULW_LOOP_STEER directive token, and the @code-yeongyu/codex-ulw-loop package. Also threads Atlas-style right-sized parallel worker delegation and a Prometheus-style QA + maximum-parallelism plan into the ulw-loop skill, with a critical post-subagent QA gate. Updates aggregate wiring (plugin package components, hooks.json, sync-skills), the install-codex agent-link test fixture, and user docs.
19 lines
507 B
JSON
19 lines
507 B
JSON
{
|
|
"aiSlopCleaner": { "status": "passed", "evidence": "no slop detected after cleaner run" },
|
|
"verification": {
|
|
"status": "passed",
|
|
"commands": ["npm test", "npm run build"],
|
|
"evidence": "all tests pass + build green"
|
|
},
|
|
"codeReview": {
|
|
"recommendation": "APPROVE",
|
|
"architectStatus": "CLEAR",
|
|
"evidence": "review synthesis: ship it"
|
|
},
|
|
"criteriaCoverage": {
|
|
"totalCriteria": 9,
|
|
"passCount": 9,
|
|
"adversarialClassesCovered": ["malformed_input", "prompt_injection", "stale_state"]
|
|
}
|
|
}
|