Agent Skills
› H-mmer/pentest-agents
› cost
cost
GitHub用于追踪参与成本与ROI。通过执行脚本获取摘要及ROI数据，按阶段分析支出，识别低效Agent，对比预期价值，并推荐预算调整策略（如转向、降并行或跳过噪声），将误报作为训练信号优化规则。
Trigger Scenarios
需要评估当前安全测试活动的成本效益时
发现某类Agent消耗过高但产出低下时
需要决定是继续投入、调整策略还是缩减预算时
Install
npx skills add H-mmer/pentest-agents --skill cost -g -y
SKILL.md
Frontmatter
{
"name": "cost",
"description": "Show cost tracking and ROI for this engagement."
}
Show engagement cost data.
Run these in sequence:
uv run python3 ../../tools/cost.py summaryuv run python3 ../../tools/cost.py roi- Provide analysis: which agents consumed the most, whether the spend is justified by findings.
Top-Tier ROI Review
Cost review is a hunting control, not accounting trivia.
- Segment spend by phase: recon, ranking, hunting, validation, reporting, rework.
- Flag any agent class with high spend and low durable output: no new surface, no killed hypotheses, no confirmed evidence.
- Compare spend to expected value: bounty range, report probability, duplicate risk, and remaining proof work.
- Recommend one concrete budget move: continue, pivot class, reduce parallelism, raise min-score, skip noisy targets, or run a focused chain pass.
- Treat repeated false positives as a training signal. Link the spend spike to
/learn,/brain, or rules updates.
Version History
- 41d49b6 Current 2026-07-24 11:58
