メニュー
Cost-quality optimization agent that analyzes tradeoffs, scores routing candidates, and proposes A/B tests. Use to generate task routing recommendations and experiment designs based on TokenAdvisor findings.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | model-engineer |
| description | Cost-quality optimization agent that analyzes tradeoffs, scores routing candidates, and proposes A/B tests. Use to generate task routing recommendations and experiment designs based on TokenAdvisor findings. |
| license | Proprietary |
| compatibility | Designed for agentic-engineers framework |
| metadata | {"author":"agentic-engineers","version":"1.0","category":"optimization","role":"senior-engineer","model":"sonnet-4-6","effort":"high","schedule":"0 17 * * *"} |
Model Engineer analyzes TokenAdvisor findings and generates cost-quality optimizations, including task routing recommendations and A/B test proposals.
What it does:
python scripts/model-engineer.py --analyze
python scripts/model-engineer.py --recommend --complexity medium
python scripts/model-engineer.py --feedback
Daily at 17:15 UTC (15 min after TokenAdvisor) via orchestration/config/model-engineer.cron
0 17 * * * sleep 900 && cd <project-root> && python agentic-engineers/skills/model-engineer/scripts/model-engineer.py --analyze
agentic-engineers/data/metrics/agentic-engineers/data/logs/model-engineer-YYYY-MM-DD.logInput: TokenAdvisor recommendations + historical metrics
Output: Feeds to A/B Testing Framework (test proposals)
Dashboard: Model Performance (Grafana)
model-engineer.py — Main optimization agent (Sonnet 4.6)This skill participates in the framework's continuous improvement cycle (see skill-improvement-feedback).
When you use model-engineer during a task, include a skill_feedback entry in your HANDBACK to help improve it over time:
skill_feedback:
- skill_name: model-engineer
effectiveness_score: 0.85 # required: 0.0–1.0
clarity_score: 0.90 # optional
coverage_gaps:
- "Specific scenario the skill did not address"
improvement_suggestions:
- "Concrete change that would have helped"
usage_context: "One sentence on how you used this skill"
Positive feedback is as valuable as critical feedback. Three or more feedback items for this skill automatically trigger an improvement task.
Experiment orchestration framework with traffic allocation, statistical analysis, and early stopping detection. Use to test routing changes, model upgrades, and role assignments with Welch's t-test significance testing.
DEPRECATED — This skill is no longer maintained. Prometheus and Grafana infrastructure was never implemented. Use local JSON metrics analysis instead.
Scaffolds new SPEC-compliant agentic-engineers agents with a single call. Generates SKILL.md frontmatter, test scaffolds (TDD RED-phase), __init__.py, scripts/ layout, and DELEGATE/HANDBACK protocol templates. Use when creating any new automation agent, task handler, or operational tool. Validates role, model, effort, naming, and dependency graphs (circular dep detection) before writing files. Supports dry-run mode for planning without side effects.
Routine maintenance for Codex sessions: monitor queue state, close completed sub-agents, resume or escalate active work, and keep agent capacity available.
Automated cross-validation of protocol queue integrity. Scans all DELEGATEs/HANDBACKs, validates schema compliance, detects cycles, checks rate limits, generates compliance report. Enables self-referential protocol improvements.
Consolidates provider-specific AI costs into unified metrics across Anthropic, OpenAI, Google Gemini, GitHub Copilot, and Ollama. Enables apples-to-apples cost comparison and savings analysis.