메뉴
Use when architecture choices need executable guardrails: dependency rules, cycle checks, boundary tests, ownership review gates, ADR compliance, runtime/resilience checks, and CI fitness functions.
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 locating, summarizing, auditing, or debugging Codex session rollout JSONL logs by CODEX_THREAD_ID, cwd, query, issue key, project path, child or inherited-history symptoms, malformed or huge log symptoms, permission concerns, or "what happened in this Codex thread" questions.
Use when auditing agent skills or plugins for safety, coverage, duplicated logic, token/context cost, prompt-contract risk, validation readiness, marketplace visibility, dependencies, network behavior, or install/update risk. For structural split/merge/move/delete/router decisions across skills or plugins, use capability-portfolio-architect instead.
Use when auditing agent skill/plugin portfolio architecture for cross-plugin capability overlap, weak routing, duplicated or missing skills, split/merge/delete/move decisions, shared capability extraction, reference/script extraction, or plugin boundary redesign. For safety, coverage, or validation review of a single artifact without boundary changes, use capability-auditor instead.
Use when performing broad external-first discovery, vetting, scoring, distillation, or synthesis of agent skills or plugin packs from the public web, GitHub/public repositories, OpenClaw/ClawHub, marketplaces, research sources, community implementations, user references, or local skills. Use for well-vetted capability synthesis, cross-skill comparison, plugin-pack synthesis, global capability acquisition, skill strengthening, and adoption/rejection changelogs.
Route and orchestrate agent skill and plugin lifecycle work. Use when work involves agent skills, plugins, marketplace packages, capability acquisition, synthesis, creation, installation, packaging, audit, or context-density optimization.
Use when creating, updating, validating, optionally installing/cache-refreshing, or handing off marketplace-backed agent plugins. Use for plugin manifests, local marketplace entries, plugin-pack synthesis, triggerable skill bundles, install visibility gates, and Codex app deeplinks.
| name | architecture-fitness-functions |
| description | Use when architecture choices need executable guardrails: dependency rules, cycle checks, boundary tests, ownership review gates, ADR compliance, runtime/resilience checks, and CI fitness functions. |
Bundled commands use $PLUGIN_ROOT ($env:PLUGIN_ROOT in PowerShell; same path suffix) for the plugin root. Set it once: use the host's plugin-root variable when defined (Claude Code: PLUGIN_ROOT="$CLAUDE_PLUGIN_ROOT"), otherwise the absolute path of this plugin's root directory.
Use when architecture quality should become observable, testable, or CI-enforced.
Each rule needs: intent, scope, owner, signal, mechanism, pass condition, cadence, failure action, exception path, related ADR/principle, protected quality attribute, and tradeoff.
Cadence: local, pre-commit, ci, release, scheduled, production.
Rollout: measure -> warn -> enforce for legacy systems.
Prefer existing project tools; add dependencies only when the boundary is important and cost is explicit.
Examples: ArchUnit/jQAssistant, NetArchTest/NDepend, dependency-cruiser/eslint/Nx graph, import-linter/pytest checks, go list, cargo metadata/clippy, SwiftPM target graph/XCTest.
Lightweight start:
python3 "$PLUGIN_ROOT/scripts/architecture_probe.py" <repo-path> --json
python3 "$PLUGIN_ROOT/scripts/architecture_probe.py" <repo-path> --json --policy <policy.json>
The probe covers top-level coupling, instability, cycles, runtime signals, ownership topology, and simple policy checks.
Use architecture_intelligence.fitness_plan.v1 or a compact table: Rule, Signal, Tool, Pass condition, Cadence, Owner.
Do not create brittle gates that block delivery without migration path.