same-session two-turn planning fixture로 run-history 신호 검증
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add zzunkie/yardlet --skill same-session-two-turn-planning-fixture-run-histo --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Same Session Two Turn Planning Fixture Run Histo?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/zzunkie-same-session-two-turn-planning-fixture-run-histo)More formats (shields.io, HTML) on the badges page.
---
name: same-session-two-turn-planning-fixture-run-histo
description: same-session two-turn planning fixture로 run-history 신호 검증
source: learned
---
planning 신호가 run 기록 projection에서 공급되는지 실제 바이너리로 검증할 때: (1) `yardlet new`로 turn 1을 만들고 `planning show --json`의 session.intent_id를 읽는다. (2) 그 intent_id로 봉인된 run 기록(run.yaml의 state failed/partial + completed_at, evaluation.json의 fatal failed check)을 temp workspace의 .agents/runs/에 seed한다. (3) `planning accept <proposal> --expected-head none` 후 `planning answer ... --expected-head <head>`로 같은 session의 turn 2를 돌리고, 두 번째 show --json의 capability_audits 전체에서 해당 hard signal 총수를 센다(turn 1은 0이어야 함). tests/fixtures/v010_002a_capability_discovery/scripts/run.sh의 repeated-failure 블록이 표준 예시다.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
