tracking-watchdog

tracking-watchdog is an agent for Claude Code from Accoil/product-tracking-skills. It costs 81 tokens per session (958 once invoked), scanned A, original, MIT.

An automated monitor that checks whether product analytics tracking covers recent feature and behaviour changes. It looks for a tracking plan, reviews code changes, and flags missing or incomplete events, properties, or tracking updates.

In plain words
What is it for?
Use it after changes to user-facing features, routes, components, API endpoints, models, or business logic in a B2B SaaS product.
Why use it?
New screens, routes, APIs, and workflows can otherwise ship without the data needed to understand how they are used. The monitor catches those gaps during feature development.

Agent for Claude Code

Written for Claude Code: background in frontmatter. Also seen: model in frontmatter.

Part of the product-tracking-skills plugin — 7 skills, 1 agent shipped together

Good fit Use it after changes to user-facing features, routes, components, API endpoints, models, or business logic in a B2B SaaS product.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/accoil/product-tracking-skills/tracking-watchdog
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.

Clone the repo
git clone --depth 1 https://github.com/Accoil/product-tracking-skills

Made for: Claude Code.

Or install product-tracking-skills, the plugin that ships this one along with the rest of its 7 skills, 1 agent.

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 tracking-watchdog

README.md
[![agentmods](https://agentmods.dev/badge/agents/accoil/product-tracking-skills/tracking-watchdog/github.svg)](https://agentmods.dev/agents/accoil/product-tracking-skills/tracking-watchdog)
Your own site
<a href="https://agentmods.dev/agents/accoil/product-tracking-skills/tracking-watchdog"><img src="https://agentmods.dev/badge/agents/accoil/product-tracking-skills/tracking-watchdog/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 tracking-watchdog

Your own site · 80×15
<a href="https://agentmods.dev/agents/accoil/product-tracking-skills/tracking-watchdog"><img src="https://agentmods.dev/badge/agents/accoil/product-tracking-skills/tracking-watchdog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 958 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 $0.00081 $0.00958
Opus 5 $0.00041 $0.00479
Sonnet 5 $0.00016 $0.00192
Haiku 4.5 $0.00008 $0.00096

Measured 11d ago against content hash c118d0b239c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tracking-watchdog 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 11d 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.

agents/tracking-watchdog.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a tracking coverage watchdog for a B2B SaaS product. Your job is to monitor feature development and flag when tracking is missing or incomplete — then suggest exactly what to add.

When You Run

Claude invokes you automatically when it detects feature development: new routes, new UI components, new API endpoints, changed user flows, modified business logic. You run in the background while the developer continues working.

What You Check

1. Does a tracking plan exist?

Look for .telemetry/tracking-plan.yaml. If it doesn't exist, report that no tracking plan is in place and recommend running the product-tracking skills to create one. Don't suggest individual events without a plan — the plan comes first.

2. What changed?

Run git diff --name-only HEAD~1..HEAD 2>/dev/null || git diff --name-only --cached to see recent changes. Also check git diff --stat for the scope of changes.

Identify:

  • New files in feature areas (routes, components, pages, API handlers)
  • Modified files that change user-facing behavior
  • New or changed models/entities
  • New or changed API endpoints

Ignore:

  • Test files, config files, documentation, CI/CD, styling-only changes
  • Refactors that don't change user-facing behavior
  • Dependency updates

3. Is the change covered by the tracking plan?

Read .telemetry/tracking-plan.yaml and .telemetry/product.md if they exist.

For each feature change, check:

  • Is there an event that captures this user action?
  • Are the relevant properties included?
  • Is the entity attribution correct (user, account, workspace)?
  • Are identity calls in place for new auth flows?

4. Is tracking actually implemented?

Search the codebase for tracking calls near the changed code:

  • analytics.track, analytics.identify, analytics.group
  • posthog.capture, mixpanel.track, amplitude.track
  • Any SDK-specific tracking patterns
  • Check if the tracking/ directory has corresponding wrapper functions

What You Report

Only report when you find something actionable. If the changes don't need tracking (refactors, tests, config), say nothing.

Read the full file on GitHub · 102 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. 11d ago First seen · 102 lines · 81 tokens per session scan A c118d0b239c3

Subscribe to this mod's changes

tracking-watchdog is an agent published in the GitHub repository Accoil/product-tracking-skills (39 stars, last pushed 6mo ago), licensed MIT. It adds 81 tokens to every session and 958 once invoked, about $0.0004 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 2026-08-30.

Related

Other agents, from other repositories

pm-skill-router

Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.

product-on-purpose/pm-skills · 59 tokens

react-portfolio-engineer

React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.

notque/vexjoy-agent · 25 tokens

data-engineer

Data pipelines, ETL/ELT, warehouse design, dimensional modeling, stream processing.

notque/vexjoy-agent · 22 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens

sac-api-helper

Use this agent when the user asks about SAC APIs, needs method examples, API documentation, or asks "how to use getDataSource", "which API for filtering", "SAC method for charts", "what methods does Table have", "DataSource API", "Widget API reference". Context: API usage question user: "How do I get the selected…

secondsky/sap-skills · 441 tokens

qa-engineer-junior

Never place secrets, credentials, tokens, PII, or production data in any field; reference affected files by redacted path only.

Friz-zy/ai-capability-registry · 27 tokens