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 reatlat/fullstory-claude-plugin --skill query-translatorgit clone --depth 1 https://github.com/reatlat/fullstory-claude-pluginWrote 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/reatlat/fullstory-claude-plugin/query-translator)<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/query-translator"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/query-translator/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/reatlat/fullstory-claude-plugin/query-translator"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/query-translator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01491 |
| Opus 5 | $0.00026 | $0.00745 |
| Sonnet 5 | $0.00010 | $0.00298 |
| Haiku 4.5 | $0.00005 | $0.00149 |
Grade A, and why
query-translator 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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query Translator
Help users who know what they want to ask but not how to phrase it for Fullstory. Turn "I want to know if people like the new feature" into measurable, query-able questions.
When to Use
- "I want to know if users are happy with the redesign — how do I ask that?"
- "What's the right way to measure engagement?"
- "I know what I want to learn but I don't know what to ask Fullstory"
- "Help me formulate a query"
- "Is there a way to measure X?"
The query-translator is invoked when the user's question is vague, abstract, or not directly answerable with Fullstory tools. It helps bridge the gap between "what I want to know" and "what Fullstory can measure."
Mental Model
Most business questions are too vague to query directly. The skill of query translation is finding a measurable proxy:
| Vague Question | Measurable Proxy |
|---|---|
| "Do users like the new feature?" | Adoption rate, repeat usage, rage clicks on the feature |
| "Is our product easy to use?" | Task completion rate, rage clicks, dead clicks, time-on-task |
| "Are users engaged?" | Session frequency, pages per session, features used, return rate |
| "Is the redesign better?" | Before/after: conversion, errors, rage clicks, scroll depth |
| "Are we losing users?" | Churn rate, at-risk user count, declining session frequency |
| "Is our support experience good?" | Sessions visiting help pages, search usage, rage clicks on help content |
Workflow
Step 1: Understand the real question
When the user asks something vague, dig deeper:
User: "I want to know if users like the new dashboard." You: "That's a great question. Let me break that down. 'Like' could mean a few different things. Are you more interested in:
- Whether they're actually using it? (adoption metrics)
- Whether they're coming back to it? (retention metrics)
- Whether they're struggling with it? (frustration metrics)
- How it compares to the old dashboard? (comparison metrics)"
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.
- 10d ago First seen · 128 lines · 51 tokens per session scan A 01f08ad4ee10
query-translator is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 28d ago), licensed MIT. It adds 51 tokens to every session and 1,491 once invoked, about $0.0003 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.
Other skills, from other repositories
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
roblox-performance
Use when profiling Roblox performance or diagnosing FPS, memory, network, mobile, or hot-path problems.
roblox-growth-design
Use for growth diagnosis, discovery, retention, onboarding, experiments, LiveOps, and packaging.
roblox-networking
Use when validating RemoteEvent or RemoteFunction arguments, adding rate limits, designing server-authoritative systems, or preventing exploits.
roblox-ui-design
Use for Roblox UI composition, hierarchy, visual systems, style inheritance, accessibility, and design review.