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 rudderlabs/rudder-agent-skills --skill rudder-tracking-reviewgit clone --depth 1 https://github.com/rudderlabs/rudder-agent-skillsWrote 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/rudderlabs/rudder-agent-skills/rudder-tracking-review)<a href="https://agentmods.dev/skills/rudderlabs/rudder-agent-skills/rudder-tracking-review"><img src="https://agentmods.dev/badge/skills/rudderlabs/rudder-agent-skills/rudder-tracking-review/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/rudderlabs/rudder-agent-skills/rudder-tracking-review"><img src="https://agentmods.dev/badge/skills/rudderlabs/rudder-agent-skills/rudder-tracking-review.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 | $0.00066 | $0.04237 |
| Opus 5.5 | $0.00026 | $0.01695 |
| Sonnet 5.5 | $0.00013 | $0.00847 |
| Haiku 4.5 | $0.00007 | $0.00424 |
Grade A, and why
rudder-tracking-review 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracking Review
The code does not show what the pipeline expects from it. RudderStack knows the tracking plan, the events that the source receives today, the transformations, and the connected destinations.
This skill has two parts: what to look for in a code change that touches analytics calls, and how to ask RudderStack about it. Use it when you review a change. Use it too when you edit such code yourself: check your edit before you report the task as done. It adds to your normal code review.
When to use this skill
| Situation | Use this skill? |
|---|---|
A task makes you add, change, rename or remove track, identify, page, screen, group or alias calls |
Yes, before you report the task as done |
| "Will this change break our tracking?" | Yes |
| A change bumps the RudderStack SDK version, or changes a wrapper around the SDK | Yes |
| Review tracking plan or data catalog YAML | No. Use rudder-tracking-plans or rudder-data-catalog |
| Review transformation code | No. Use rudder-transformations |
| Events fail at a destination in production | No. Use rudder-destination-debugging |
AI events (ai_*, mcp_*) |
No. Use rudder-ai-events-verify |
When you made the change yourself
A task that renames an event, adds a property or changes a call looks done when the code and the tests pass. The pipeline can still drop the event. Before you report the task as done:
- Find the source that receives the events of the app. "How RudderStack helps" says how.
- Read its tracking plan and plan settings. Compare each event and property that you touched.
- Read the transformations and the destination settings on that source. Search them for each name that you changed.
- Tell the user what you found, in the same message as the result of the task. Say what breaks and what to change in RudderStack first, or say what you could not check.
Do these checks yourself, with the tools. Do not only tell the user to do them.
What to look for
Look at each analytics call that the change adds, alters or removes. A change to the SDK version counts too, and so does a change to a wrapper around the SDK.
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.
- today First seen · 168 lines · 66 tokens per session scan A 92ffd31b7c58
rudder-tracking-review is a skill published in the GitHub repository rudderlabs/rudder-agent-skills (19 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 4,237 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 2026-11-14.
rudder-tracking-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rudder-tracking-reviewrudderlabs/rudder-agent-skills | Skill | 19 | yesterday | MIT | A | 66 | Claude Code |
| scientific-figure-prompt-compilerbasejb/skills | Skill | 5 | 2mo ago | none | A | 72 | Claude Code |
| seo-optimizerbasejb/skills | Skill | 5 | 2mo ago | none | A | 60 | Claude Code |
| ai-collab-evaluatorbasejb/skills | Skill | 5 | 2mo ago | none | A | 169 | Claude Code |
| learning-companionbasejb/skills | Skill | 5 | 2mo ago | none | A | 134 | Claude Code |
| oss-tourbasejb/skills | Skill | 5 | 2mo ago | none | A | 106 | Claude Code |
| image-optimizerbasejb/skills | Skill | 5 | 2mo ago | none | A | 43 | Claude Code |