跳到正文
cccskills
免费在 GitHub 公开

cost-anomaly

Identify individual sessions with unusually high or low spending using the median and MAD, a measure of spread around it. Filter by time period, adjust detection thresholds, and optionally return a failure exit code for automated checks.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

MAD-based outlier detection on session spend. Robust to the very outliers it hunts (unlike mean+sigma). Surfaces specific anomalous sessions with modified-z scores; optional --alert-on-outliers exit code for CI gates. Distinct from cost-burn (aggregate trend) — this answers "which INDIVIDUAL session is the outlier?".

查看安装方法

适用场景

  • Find sessions with unusually high spending
  • Check sessions with unusually low spending
  • Review spending anomalies over the past week
  • Fail a CI check when outlier counts reach a limit

包含的文件(1)

  • SKILL.md3.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Per-session outlier detection — the diagnostic counterpart to cost-burn's aggregate-trend signal.

QuestionSkill
"Is the AGGREGATE rate accelerating?"cost-burn
"Which SPECIFIC sessions are anomalous outliers?"cost-anomaly ← this
"Could we have spent less in aggregate?"cost-counterfactual
"When will we hit budget?"cost-projection

Algorithm

Implementation: scripts/anomaly.mjs.

  1. Read all session-* records from cost-tracking namespace.
  2. Filter to --since window (default: all-time).
  3. Compute median(total_cost_usd) and MAD = median(|x - median|).
  4. Per-session modified z-score (Iglewicz-Hoaglin 1993): z = 0.6745 * (x - median) / MAD
  5. Flag sessions with |z| > --threshold (default 3.5).

Why MAD and not mean + sigma?

ApproachWhat breaks
mean + sigmaA single $50 session inflates BOTH mean and sigma so badly that subsequent outliers hide inside the new "normal" band. Catastrophic on small samples.
median + MADBoth estimators ignore up to 50% of the data — the outliers themselves can't shift them. Robust on n=10. The canonical cutoff |z| > 3.5 is from Iglewicz-Hoaglin (1993).

Smoke transcript (5 baseline sessions $0.08-$0.12 + 1 outlier $5.00)

| Sessions considered | 5 |
| Threshold (|modified z|) | 3.5 |
| Median spend | $0.100000 |
| MAD | $0.010000 |
| Min / Max | $0.080000 / $5.000000 |
| **Outliers found** | **1** |

## Outlier sessions
| Session | Spend | Deviation | Modified z | Direction |
| outlier- | $5.000000 | +$4.900000 | 330.505 | high |

Exit codes

$ cost anomaly --alert-on-outliers 1
⚠ ALERT: found 1 outlier session(s) (|modified z| > 3.5); threshold was ≥1
exit 1

$ cost anomaly --alert-on-outliers 5
✓ found 1 outlier session(s); under threshold ≥5 — OK
exit 0

CI integration

# Fail the build if any session this week is a >3.5σ outlier
cost anomaly --since 7d --alert-on-outliers 1 || investigate-bad-session

Most useful when paired with cost-burn:

cost burn  --alert-on-acceleration-pct 50  || page-oncall   # rate-of-change alert
cost anomaly --alert-on-outliers 1         || investigate   # point-anomaly alert

Together they cover "is the average shifting?" AND "is there a single rogue session?" — both can fire independently.

Edge cases

  • n < 3: emit "Insufficient data" message, exit 0. MAD on 1-2 samples is meaningless.
  • MAD = 0: ≥50% of sessions share the exact same spend, so z-scores collapse. Emit explainer instead of dividing by zero. Common cause: dry-run sessions all at $0.
  • Low-direction outliers: usually crashed or dropped sessions, not over-spending. The output table explicitly labels direction so operators interpret correctly.
  • Very small MAD: even tiny absolute deviations produce huge z-scores. The $5 outlier with MAD=$0.01 yields z=330 — that's correct, not a bug.

Direction column

DirectionLikely causeAction
highLong session, stuck in expensive tier, or runaway loopcost report + cost conversation to investigate
lowCrash, dropped session, or unfinished workVerify the session completed normally

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.

中文简介正在准备中。当前显示英语简介。

  • Adding newly available router models to chat-ui
  • Writing concise descriptions of model capabilities
  • Updating production and development model entries together
ruvnet/ruflo7.7万2026年10月19日 更新

Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.

中文简介正在准备中。当前显示英语简介。

  • Record the reasoning behind adopting a technology
  • Start an ADR for an API or data model change
  • Document an infrastructure decision
ruvnet/ruflo7.7万2026年10月19日 更新

adr-index

免费

Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.

中文简介正在准备中。当前显示英语简介。

  • Index ADRs imported from another project
  • Refresh a graph that differs from files on disk
  • Set up ADR tracking in an existing codebase
ruvnet/ruflo7.7万2026年10月19日 更新

Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.

中文简介正在准备中。当前显示英语简介。

  • Rebuild the index after deleting an ADR file
  • Remove stale relationships after editing an ADR
  • Reconcile the ADR index on a schedule
ruvnet/ruflo7.7万2026年10月19日 更新

Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.

中文简介正在准备中。当前显示英语简介。

  • Check a pull request before merging
  • Review major code changes against agreed design decisions
  • Find references to superseded ADRs
ruvnet/ruflo7.7万2026年10月19日 更新

Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.

中文简介正在准备中。当前显示英语简介。

  • Checking ADR integrity after import
  • Blocking CI when ADR issues are found
  • Reviewing ADR data before a release
ruvnet/ruflo7.7万2026年10月19日 更新

查看 ruvnet 的全部技能

报告此技能的问题