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 thuong-nc/perlytics-skill --skill cohort-retentiongit clone --depth 1 https://github.com/thuong-nc/perlytics-skillWrote 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/thuong-nc/perlytics-skill/cohort-retention)<a href="https://agentmods.dev/skills/thuong-nc/perlytics-skill/cohort-retention"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/cohort-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/thuong-nc/perlytics-skill/cohort-retention"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/cohort-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 | $0.00029 | $0.00475 |
| Opus 5 | $0.00015 | $0.00237 |
| Sonnet 5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
cohort-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 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cohort Retention
Purpose
Analyze retention with explicit cohort logic so the result actually means something.
When to use
Use this skill when:
- the question is about return behavior over time
- a team is using retention language loosely
- you need to compare cohorts, channels, or product changes
When not to use
Do not use this skill when:
- the task is about a one-time conversion flow
- the return rule is not meaningful for the product or business model
Required thinking discipline
- Define the cohort entry rule.
- Define the retained behavior.
- Define the time interval and retention horizon.
- Distinguish retention from reactivation and expansion.
- Evidence constraint: Every conclusion must cite specific data — a number, a rate, a segment, or a timeframe. Do not speculate without evidential basis. If data is insufficient, state what is missing rather than asserting an unsupported inference.
Workflow
- Define the entity: user, account, buyer, team, or merchant.
- Define cohort membership.
- Define retained behavior and return window.
- Choose the horizon and cadence.
- Compare cohorts across useful segments.
- Interpret differences carefully with lifecycle context.
Output format
- Cohort definition
- Retention definition
- Horizon and cadence
- Cohort comparison summary
- Segment differences
- Caveats and likely drivers
Good example
Cohort = first-paid-month account cohorts. Retention = account records at least one paid invoice in each subsequent month. Compare 6-month retention by acquisition channel.
Bad example
Retention is how many users keep using the product.
Why this is bad:
- cohort entry is missing
- return rule is missing
- time cadence is missing
Practical notes
- Say whether you are showing classic retention, rolling retention, or returning activity.
- Be careful when product usage is irregular by design.
Optional variants
- Marketplace businesses: distinguish buyer and seller retention.
- B2B SaaS: decide whether retention is user-level or account-level.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 78 lines · 29 tokens per session scan A 6d9af7287110
cohort-retention is a skill published in the GitHub repository thuong-nc/perlytics-skill (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 475 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
sn-image-imitate
An image tool that creates new content while following the visual style and layout of a single reference image.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.