agentmods.dev

dynt-anomaly-triage

dynt-anomaly-triage is a skill for Claude Code from bpais88/dynt-agent-skills. It costs 76 tokens per session (403 once invoked), scanned A, original, MIT.

A read-only guide for reviewing data-quality problems in Dynt, such as duplicate merchants, unusual charges, and missing categories. It explains how to rate each problem and support it with transaction evidence.

In plain words
What is it for?
Use it to summarize and prioritize Dynt anomalies, investigate suspected double charges, and recommend the appropriate cleanup step.
Why use it?
It turns a list of possible problems into a prioritized explanation and a clear next action, reducing the chance of calling a transaction a duplicate without checking it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dynt plugin — 7 skills shipped together

not rated 0repo 28d ago A scan 76 tokens original MIT

Good fit Use it to summarize and prioritize Dynt anomalies, investigate suspected double charges, and recommend the appropriate cleanup step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bpais88/dynt-agent-skills/dynt-anomaly-triage
View source ↗ bpais88/dynt-agent-skills
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 bpais88/dynt-agent-skills --skill dynt-anomaly-triage
Clone the repo
git clone --depth 1 https://github.com/bpais88/dynt-agent-skills

Made for: Claude Code.

Or install dynt, the plugin that ships this one along with the rest of its 7 skills.

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 dynt-anomaly-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/bpais88/dynt-agent-skills/dynt-anomaly-triage/github.svg)](https://agentmods.dev/skills/bpais88/dynt-agent-skills/dynt-anomaly-triage)
Your own site
<a href="https://agentmods.dev/skills/bpais88/dynt-agent-skills/dynt-anomaly-triage"><img src="https://agentmods.dev/badge/skills/bpais88/dynt-agent-skills/dynt-anomaly-triage/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 dynt-anomaly-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/bpais88/dynt-agent-skills/dynt-anomaly-triage"><img src="https://agentmods.dev/badge/skills/bpais88/dynt-agent-skills/dynt-anomaly-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 403 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 $0.00076 $0.00403
Opus 5.5 $0.00030 $0.00161
Sonnet 5.5 $0.00015 $0.00081
Haiku 4.5 $0.00008 $0.00040

Measured 2mo ago against content hash e56d9a5c83ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dynt-anomaly-triage 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 2mo 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.

plugins/dynt/skills/dynt-anomaly-triage/SKILL.md · 35 lines

What it actually says

FIRST: read the parent dynt skill for connection, safety rules and tool families.

Anomaly triage

Outcome: each open anomaly has a severity, a one-line explanation and a next step. Read-only.

  1. get_anomaly_summary → open / acknowledged / resolved counts. If the server offers list_findings, call it first: price increases, stopped subscriptions, duplicate charges and missing-receipt clusters arrive pre-computed with evidence and money at stake — do not recompute them; use the steps below for what findings do not cover.

  2. list_anomalies → for each: type, severity, description, affected record.

  3. For suspected double charges, pull the two transactions with list_transactions (merchantName + a tight date window) and compare amount, date and account before calling it a duplicate.

  4. Group by type; order by severity then amount at stake.

Present a table: severity · type · what happened · evidence · next step. Next steps map to skills: duplicate merchant → dynt-transaction-cleanup; missing receipt → dynt-receipt-compliance; recurring charge change → dynt-subscription-audit. Resolving or acknowledging anomalies happens in the Dynt app; say so rather than implying you changed their status.

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. 2mo ago First seen · 35 lines · 76 tokens per session scan A e56d9a5c83ef

Subscribe to this mod's changes

dynt-anomaly-triage is a skill published in the GitHub repository bpais88/dynt-agent-skills (0 stars, last pushed 28d ago), licensed MIT. It adds 76 tokens to every session and 403 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Analytics and metrics
Related

dynt-anomaly-triage compared with skills from other repositories

dynt-anomaly-triage next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dynt-anomaly-triagebpais88/dynt-agent-skillsSkill028d agoMITA76Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code