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 cohort-compassgit 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/cohort-compass)<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/cohort-compass"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/cohort-compass/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/cohort-compass"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/cohort-compass.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 | $0.00045 | $0.00904 |
| Opus 5 | $0.00023 | $0.00452 |
| Sonnet 5 | $0.00009 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
cohort-compass 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cohort Compass
Build, manage, and compare user cohorts. Keeps segments consistent across multiple analyses so you don't rebuild the same cohort five times in one conversation.
When This Runs
Invoked automatically by general-analysis, comparisons, funnel-doctor, and weekly-digest when they need cohort-level analysis. Not user-invocable directly — it's a supporting skill that keeps the other skills consistent.
What Cohorts Are
A cohort is a segment that persists across analyses. Examples:
- Enterprise users (plan = enterprise)
- New users (first_seen in last 30 days)
- Power users (total_sessions > 20)
- German users (country = DE)
- Mobile-only users (device = mobile, no desktop sessions)
The key difference from one-off segments: cohorts get reused. You build the "enterprise users" segment once, then attach it to multiple metrics — error rate, conversion, page views, frustration signals — without rebuilding.
Workflow
Step 1: Build the cohort
When a skill needs a cohort (e.g., "compare enterprise vs free users"):
fullstory:build_segment("users on enterprise plan")
→ returns segment_id
Name it clearly in the query so the segment is findable later. "enterprise plan users" not "segment 1".
Step 2: Track it
Keep a running list of segments built in the conversation:
seg_ent: enterprise usersseg_free: free usersseg_new: users with first_seen in last 30 days
When a later question needs the same cohort, reuse the segment_id. Don't rebuild.
Step 3: Compute per cohort
For each cohort, attach the segment, compute, store the result:
fullstory:update_metric(metric_id, segment_id=seg_ent)
fullstory:compute_metric(metric_id) → store result
fullstory:update_metric(metric_id, segment_id=seg_free)
fullstory:compute_metric(metric_id) → store result
Step 4: Compare
Present results side by side:
Checkout completion rate (last 30 days)
Enterprise: 31% (3,100 / 10,000)
Free: 18% (5,400 / 30,000)
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 · 95 lines · 45 tokens per session scan A 4e194ee5dfcc
cohort-compass is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 29d ago), licensed MIT. It adds 45 tokens to every session and 904 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.