da-anomaly-analysis

da-anomaly-analysis is a skill for Claude Code, Codex from ShenSeanChen/waku-agent. It costs 42 tokens per session (558 once invoked), scanned A, original, MIT.

A method for investigating unusual changes in business metrics such as daily active users, revenue, conversion, retention, or gross merchandise value. It first checks whether the data change is real before looking for causes.

In plain words
What is it for?
Use it to define the comparison, validate source data, break a metric into funnels or groups, quantify each group’s contribution, and then examine internal and external causes.
Why use it?
It reduces the risk of blaming business activity for a measurement, instrumentation, data-pipeline, timing, or scope problem.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to define the comparison, validate source data, break a metric into funnels or groups, quantify each group’s contribution, and then examine internal and external causes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shenseanchen/waku-agent/da-anomaly-analysis
About the project

Waku Agent is a local-first personal AI assistant whose readable code implements the agent loop, memory, and evaluation system. It is for people who want an assistant they can run and understand on their own laptop, with memory stored in SQLite and built-in testing. The catalogue add-ons support its agent workflow.

ShenSeanChen/waku-agent · 1,728 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ShenSeanChen/waku-agent --skill da-anomaly-analysis
Clone the repo
git clone --depth 1 https://github.com/ShenSeanChen/waku-agent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for da-anomaly-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/shenseanchen/waku-agent/da-anomaly-analysis/github.svg)](https://agentmods.dev/skills/shenseanchen/waku-agent/da-anomaly-analysis)
Your own site
<a href="https://agentmods.dev/skills/shenseanchen/waku-agent/da-anomaly-analysis"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/da-anomaly-analysis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for da-anomaly-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/shenseanchen/waku-agent/da-anomaly-analysis"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/da-anomaly-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00558
Opus 5 $0.00021 $0.00279
Sonnet 5 $0.00008 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured today against content hash 35ba20f1d4d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

da-anomaly-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/community/da-anomaly-analysis/SKILL.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions

Follow this sequence: define the anomaly, validate the data, narrow the source, investigate internal causes, then investigate external causes. Confirm that the change is real before explaining it.

  1. Define the anomaly. State the metric definition, time window, comparison baseline, start time, duration, absolute and relative change, business magnitude, and affected scope.
  2. Validate the data. Check source data, instrumentation, ETL, latency, metric definitions, scope changes. Stop business attribution until data and normal periodicity are cleared.
  3. Narrow the source. Start with a business equation or funnel, then drill down by mutually exclusive and collectively exhaustive groups such as time, region, channel, platform, version, product, and user segment. Iterate between formula decomposition and dimension drill-down.
  4. Quantify contribution. Choose the method from the mathematical relationship:
  • Additive total, S = sum(s_i): use delta_i = s_i_now - s_i_base; contribution share is delta_i / delta_S.
  • Weighted rate, Y = sum(w_i * y_i): decompose each group into quality w_i_base * delta_y_i, structure delta_w_i * (y_i_base - Y_base), and interaction delta_w_i * delta_y_i.
  • Multiplicative metric, S = A * B * ...: use relative-change, log, or Shapley decomposition and apply one consistent interaction-allocation rule. Report contribution values, directions, and shares. If total change is near zero or opposing effects offset, emphasize values because shares may be unstable, negative, or above 100%.
  1. Investigate internal causes. Form falsifiable hypotheses around product releases, algorithms, supply, campaigns, budgets, targeting, configuration, outages, performance, compatibility, and reporting. For each hypothesis, specify the change record, timing, affected scope, expected mechanism, validation metric, and control.
  2. Investigate external causes. Check market trends, competitors, policy, public events, holidays, weather, and seasonality. Validate with industry data, historical periods, unaffected groups, or comparable markets.
  3. Deliver the decision. Summarize the primary and secondary drivers, evidence strength, unresolved hypotheses, immediate mitigation, long-term prevention, owner, and recovery monitoring.

Read the full file on GitHub · 29 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 29 lines · 0 tokens per session scan A 35ba20f1d4d4

Subscribe to this mod's changes

da-anomaly-analysis is a skill published in the GitHub repository ShenSeanChen/waku-agent (1,728 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 558 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.