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 metric-auditorgit 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/metric-auditor)<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/metric-auditor"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/metric-auditor/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/metric-auditor"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/metric-auditor.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 | $0.00047 | $0.00987 |
| Opus 5 | $0.00023 | $0.00494 |
| Sonnet 5 | $0.00009 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
metric-auditor 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 12d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metric Auditor
Audit your Fullstory account — find duplicate metrics, stale segments nobody uses, misconfigured objects, and naming inconsistencies. Keeps the shared workspace clean so the team trusts the numbers.
When This Runs
Invoked automatically when general-analysis finds multiple candidates for a search and needs to determine which one is canonical. Also runs when the user explicitly asks:
- "Are there duplicate metrics in our account?"
- "Clean up our segments — which ones are stale?"
- "What metrics exist for checkout?"
- "Is anyone actually using this segment?"
Mental Model
Fullstory accounts accumulate cruft over time — metrics built for a one-off question, segments created for a meeting three months ago, copies of copies with slightly different names. This skill finds and diagnoses that cruft.
Workflow
Step 1: Discover everything
Search broadly to get the lay of the land:
fullstory:get_metric(regex="") → list all metrics
fullstory:get_segment(regex="") → list all segments
If the account is large, narrow by keyword: fullstory:get_metric(regex="checkout").
Step 2: Check popularity
For every object found, call fullstory:get_view_count (up to 10 IDs at a time):
- High view count: Actively used — canonical, trusted.
- Low view count: Maybe stale — built once, never referenced again.
- Zero views: Almost certainly stale — safe to flag for cleanup.
Step 3: Identify issues
Duplicates: Two metrics with nearly identical names and the same output type. Example: "checkout conversion" and "checkout conversion rate" both returning single_number. Flag: pick the one with higher view count as canonical.
Stale objects: Zero views and created more than 30 days ago. Flag for deletion.
Naming problems: "Untitled metric", "Segment 1", "Copy of checkout funnel". Suggest renaming.
Misconfigured: A segment that filters by a property that no longer exists, or a trend metric built as single_number. These are harder to detect without computing — flag if the name doesn't match the output type.
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.
- 12d ago First seen · 95 lines · 47 tokens per session scan A cf844c1143a3
metric-auditor is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 29d ago), licensed MIT. It adds 47 tokens to every session and 987 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.