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 page-performancegit 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/page-performance)<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/page-performance"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/page-performance/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/page-performance"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/page-performance.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 | $0.00043 | $0.00928 |
| Opus 5 | $0.00022 | $0.00464 |
| Sonnet 5 | $0.00009 | $0.00186 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
page-performance 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Page Performance
Analyze page-level health — load times, errors, device breakdown, and how users navigate between pages.
When to Use
- "Which pages have the most errors?"
- "How does /checkout perform on mobile vs desktop?"
- "What pages do users visit before /pricing?"
- "Show me sessions where /dashboard was slow to load"
- "Which pages have the highest abandonment rate?"
- "Compare all product pages by error rate"
Workflow
Step 1: Define the scope
What does the user want to know about the page(s)?
- Error rate: console errors, network failures on this page
- Performance: rage clicks, dead clicks, form abandonment on this page
- Navigation: what pages lead to/from this page
- Device breakdown: mobile vs desktop usage and error rates
- Comparison: rank multiple pages by a metric
Step 2: Build page-scoped metrics
For a single page, scope the metric to that page:
fullstory:build_metric(
query="console errors on /checkout",
output_type="trend" # or single_number or top_n
)
For comparing multiple pages, use top_n grouped by page:
fullstory:build_metric(
query="console errors by page",
output_type="top_n"
)
Step 3: Add device/browser breakdown
If the user wants to know "mobile vs desktop on this page":
fullstory:build_metric(
query="page views on /checkout by device type",
output_type="top_n"
)
Or for errors specifically:
fullstory:build_metric(
query="console errors on /checkout by device type",
output_type="top_n"
)
Step 4: Investigate problem pages
If a page stands out (high error rate, high abandonment):
fullstory:get_sessions(page="/checkout", metric_id=error_metric_id, limit=5)- Load sessions through
session-contextagent: "What error occurred on /checkout? What page did the user come from and go to?" - Synthesize: is the error specific to this page, or does it follow the user from a previous page?
Step 5: Navigation patterns
To understand what pages users visit before/after a given page:
fullstory:get_user_pages(uid="...", options={...})
→ returns all pages visited by a user in order
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.
- 11d ago First seen · 107 lines · 43 tokens per session scan A 1cd1beee4a58
page-performance is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 29d ago), licensed MIT. It adds 43 tokens to every session and 928 once invoked, about $0.0002 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.