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 bjorn-ingmanson/thefroject-plugins --skill diagnose-retentiongit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-pluginsWrote 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/bjorn-ingmanson/thefroject-plugins/diagnose-retention)<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/diagnose-retention"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/diagnose-retention/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/bjorn-ingmanson/thefroject-plugins/diagnose-retention"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/diagnose-retention.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 | $0.00043 | $0.01059 |
| Opus 5.5 | $0.00017 | $0.00424 |
| Sonnet 5.5 | $0.00009 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
diagnose-retention 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 2mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retention Diagnostician
Retention is the foundation of sustainable growth. A product with strong acquisition but poor retention is a leaky bucket. Fix the bucket before pouring more water.
Phase 1 — Measure Retention
Define the Retention Event
What action indicates a user is still getting value? This may differ from activation:
- Activation event: First time the user gets value
- Retention event: Repeated action that signals ongoing value
| Product Type | Typical Retention Event | Frequency |
|---|---|---|
| SaaS tool | Core feature used | Weekly |
| Marketplace | Transaction completed | Monthly |
| Content platform | Content consumed | Daily/Weekly |
| Communication tool | Message sent | Daily |
Your retention event: [define it] Expected frequency: [how often a healthy user does it]
Build the Retention Curve
Plot the percentage of users who return at each time interval after activation:
| Time Period | Cohort Size | Users Retained | Retention Rate |
|---|---|---|---|
| Week 0 | [n] | [n] | 100% |
| Week 1 | [n] | [n] | [%] |
| Week 4 | [n] | [n] | [%] |
| Week 8 | [n] | [n] | [%] |
| Week 12 | [n] | [n] | [%] |
Key metrics:
- Day 1 retention: Early engagement signal
- Week 1 retention: Habit formation indicator
- Flattening point: Where the curve levels off — this is your stable retained base
Phase 2 — Segment the Curve
Compare retention across segments to find what separates users who stay from users who leave:
Behavioral Segments
| Segment | Week-4 Retention | Notes |
|---|---|---|
| Activated in first 24h | [%] | |
| Activated in day 2-7 | [%] | |
| Used feature X | [%] | |
| Connected integration | [%] | |
| Invited a teammate | [%] |
Acquisition Segments
| Channel | Week-4 Retention | Notes |
|---|---|---|
| Organic search | [%] | |
| Paid acquisition | [%] | |
| Referral | [%] | |
| Direct | [%] |
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.
- 2mo ago First seen · 116 lines · 43 tokens per session scan A 98666cd37823
diagnose-retention is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,059 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
diagnose-retention compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diagnose-retentionbjorn-ingmanson/thefroject-plugins | Skill | 1 | 4mo ago | MIT | A | 43 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |