메뉴
Use when you need to run plugin consistency checks or drift detection.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when you have a large-scale, multi-phase project requiring orchestrated execution.
Use when you need persistent looping until a task is fully complete.
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, completeness + interaction critics, and a deterministic 3-lens rubric judge panel. Opt-in main-loop Workflow tier.
Use when the user wants to review accumulated skill feedback, verdict trends, or improvement candidates collected during Stage 4 retrospectives. Trigger on "show skill feedback", "스킬 피드백 보여줘", or finding which skills need /writing-skills work.
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
| name | team-shinchan:lint-harness |
| description | Use when you need to run plugin consistency checks or drift detection. |
| user-invocable | false |
Check plugin consistency and detect configuration drift.
/team-shinchan:lint-harness # Full check (JSON)
/team-shinchan:lint-harness --category agents # Agent consistency only
/team-shinchan:lint-harness --category structure # Structural integrity only
/team-shinchan:lint-harness --category drift # Drift detection only
/team-shinchan:lint-harness --format table # Colored text table
| Arg | Default | Description |
|---|---|---|
--category {name} | (all) | Check only: agents, structure, or drift |
--format {fmt} | json | Output format: json or table |
Execute the harness lint script:
node ${CLAUDE_PLUGIN_ROOT}/src/harness-lint.js [args]
Show the output from the lint script directly to the user.
After displaying results, provide a brief summary:
Harness Lint: {passed}/{total} checks passed
{list any FAIL items with recommended fixes}
| Category | What it checks |
|---|---|
| agents | Required frontmatter, coding-principles refs, maxTurns, permissionMode |
| structure | Skill-command parity, hook registration, cross-refs, layer-map |
| drift | Output-formats refs, self-check refs, version consistency, ARCHITECTURE.md staleness, Assumption Audit (Skepticism Rules, Sprint-Contract, eval-rubrics.json, resume handoff) |
.shinchan-docs/.last-lint timestamp after running