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 CodePhobiia/claude-roblox-game-studio --skill retention-analysisgit clone --depth 1 https://github.com/CodePhobiia/claude-roblox-game-studioWrote 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/codephobiia/claude-roblox-game-studio/retention-analysis)<a href="https://agentmods.dev/skills/codephobiia/claude-roblox-game-studio/retention-analysis"><img src="https://agentmods.dev/badge/skills/codephobiia/claude-roblox-game-studio/retention-analysis/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/codephobiia/claude-roblox-game-studio/retention-analysis"><img src="https://agentmods.dev/badge/skills/codephobiia/claude-roblox-game-studio/retention-analysis.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 | $0.00033 | $0.00827 |
| Opus 5 | $0.00016 | $0.00413 |
| Sonnet 5 | $0.00007 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
retention-analysis 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 9d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/retention-analysis — Retention Metrics Analysis
Delegate to: analytics-retention-specialist
Steps
1. Gather Data
Ask the user to provide or pull from Roblox Analytics:
- Retention: D1, D7, D30 percentages (current + last 30 days)
- Sessions: Average session length, sessions per day per user
- Funnel: New player funnel step completion rates
- Concurrent Users: Peak CCU, average CCU trends
- Revenue: ARPDAU, conversion rate (if applicable)
- Platform split: Mobile vs. PC vs. console %
2. Benchmark Against Targets
| Metric | Target | Current | Delta | Status |
|---|---|---|---|---|
| D1 Retention | > 25% | ?% | ? | 🟢/🟡/🔴 |
| D7 Retention | > 12% | ?% | ? | 🟢/🟡/🔴 |
| D30 Retention | > 5% | ?% | ? | 🟢/🟡/🔴 |
| Avg Session | > 15 min | ? | ? | 🟢/🟡/🔴 |
| Sessions/Day | > 1.5 | ? | ? | 🟢/🟡/🔴 |
| Conversion | > 3% | ?% | ? | 🟢/🟡/🔴 |
3. Identify Weakness
Which metric is furthest from target? That's the priority.
4. Hypothesis Generation
For the weak metric, brainstorm causes:
Low D1 Retention:
- FTUE is confusing or slow
- No first-session reward
- Performance issues on first load
- Crashes on first play
Low D7 Retention:
- No reason to come back
- Daily reward not compelling
- Content runs out quickly
- Social features missing
Low Session Length:
- Session loop too short
- Nothing to do after core loop
- AFK handling kicks players
Low Conversion:
- Monetization not discoverable
- Items not appealing
- Too expensive for perceived value
- Pay-to-win pushback
5. Recommend Experiments
For top 2-3 hypotheses, recommend experiments:
- Change: What to change
- Measure: What metric will tell us if it worked
- Duration: How long to run
- Sample: How many players needed
6. Generate Report
Save to production/analytics/retention-<date>.md on approval using .claude/docs/templates/retention-report-template.md.
# Retention Analysis: [Period]
**Date**: YYYY-MM-DD
**Period analyzed**: [start] to [end]
## Summary
[1-3 sentences on overall health]
## Metric Status
[Table from step 2]
## Primary Concern
**[Metric name]** is [X%] below target.
## Hypotheses
1. [Hypothesis 1 with reasoning]
2. [Hypothesis 2 with reasoning]
3. [Hypothesis 3 with reasoning]
## Recommended Experiments
### Experiment A: [Name]
- Hypothesis: [What we think will work]
- Change: [Specific change to make]
- Measure: [Metric to watch]
- Duration: 7 days
- Required sample: 500 players per variant
## Next Steps
1. Decide which experiment to run first
2. Implement via live-ops-specialist
3. Monitor metric daily
4. Review results in 7-14 days
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.
- 9d ago First seen · 104 lines · 33 tokens per session scan A 09952670d693
retention-analysis is a skill published in the GitHub repository CodePhobiia/claude-roblox-game-studio (9 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 827 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 2026-09-03.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.