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.
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.
npx skills add ShenSeanChen/waku-agent --skill da-anomaly-analysisgit clone --depth 1 https://github.com/ShenSeanChen/waku-agentWrote 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.
[](https://agentmods.dev/skills/shenseanchen/waku-agent/da-anomaly-analysis)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00558 |
| Opus 5.5 | $0.00000 | $0.00223 |
| Sonnet 5.5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
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 1mo ago.
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.
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.
- Define the anomaly. State the metric definition, time window, comparison baseline, start time, duration, absolute and relative change, business magnitude, and affected scope.
- Validate the data. Check source data, instrumentation, ETL, latency, metric definitions, scope changes. Stop business attribution until data and normal periodicity are cleared.
- 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.
- 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%.
- 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.
- 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.
- Deliver the decision. Summarize the primary and secondary drivers, evidence strength, unresolved hypotheses, immediate mitigation, long-term prevention, owner, and recovery monitoring.
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.
- 1mo ago First seen · 29 lines · 0 tokens per session scan A 35ba20f1d4d4
da-anomaly-analysis is a skill published in the GitHub repository ShenSeanChen/waku-agent (2,105 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 558 tokens. 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.
Other skills, from other repositories
migrating-mastra-to-pydantic-ai
Migrate TypeScript Mastra applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports @mastra/ or relies on Mastra agents, tools, workflows, memory, processors, streaming, approvals, skills, or subagents.
migrating-vercel-ai-sdk-and-eve-to-pydantic-ai
Migrate TypeScript Vercel AI SDK or Eve applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports ai, @ai-sdk/, or eve, or relies on generateText, streamText, ToolLoopAgent, useChat, Eve agents, tools, skills, subagents, approvals, sessions, channels, schedules…
migrating-openai-agents-sdk-to-pydantic-ai
Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness. Use for agents.Agent, Runner, function tools, handoffs, guardrails, sessions, human approval, streaming, or SandboxAgent. Do not use for applications built directly on the OpenAI Responses API without the Agents SDK…
slacrawl
Archive and search Slack workspace messages, threads, and channels via the slacrawl CLI. Supports API sync, Slack export ZIP import, local desktop cache import, and full-text search.
obsidian
Read, search, and create notes in the Obsidian vault.
hep-search
Search Agentlas Cloud and Hub agent candidates without invoking.