retention-cohorts

retention-cohorts is a skill for Claude Code from VoxTechnologies/anty-framework. It costs 78 tokens per session (1,325 once invoked), scanned A, original, MIT.

A method for studying how groups of users continue using a product over time. A cohort is a group that started or took a key action during the same period, such as one month.

In plain words
What is it for?
Use it to build retention tables and charts, assess product-market fit, find retention problems, and choose between improving the product and investing in growth.
Why use it?
It helps separate real user retention from temporary sign-ups and shows whether usage is falling, stabilising, or growing after the first use.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the anty plugin — 24 skills, 11 commands, 4 agents shipped together

Good fit Use it to build retention tables and charts, assess product-market fit, find retention problems, and choose between improving the product and investing in growth.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/voxtechnologies/anty-framework/retention-cohorts
Install

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.

Any agent
npx skills add VoxTechnologies/anty-framework --skill retention-cohorts
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/anty-framework

Made for: Claude Code.

Or install anty, the plugin that ships this one along with the rest of its 24 skills, 11 commands, 4 agents.

Wrote 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.

agentmods badge for retention-cohorts

README.md
[![agentmods](https://agentmods.dev/badge/skills/voxtechnologies/anty-framework/retention-cohorts/github.svg)](https://agentmods.dev/skills/voxtechnologies/anty-framework/retention-cohorts)
Your own site
<a href="https://agentmods.dev/skills/voxtechnologies/anty-framework/retention-cohorts"><img src="https://agentmods.dev/badge/skills/voxtechnologies/anty-framework/retention-cohorts/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.

agentmods 80×15 button for retention-cohorts

Your own site · 80×15
<a href="https://agentmods.dev/skills/voxtechnologies/anty-framework/retention-cohorts"><img src="https://agentmods.dev/badge/skills/voxtechnologies/anty-framework/retention-cohorts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,325 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.01325
Opus 5 $0.00039 $0.00662
Sonnet 5 $0.00016 $0.00265
Haiku 4.5 $0.00008 $0.00133

Measured 10d ago against content hash 7421f54d273a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

retention-cohorts 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/retention-cohorts/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retention & Cohort Analysis

When to Apply

  • Measuring product-market fit
  • Deciding whether to invest in growth vs product improvement
  • When the founder asks "do we have PMF?"
  • When retention data is available from integrations
  • Quarterly PMF reassessment

Core Framework

Three Definitions (Set During Onboarding)

Before any retention measurement, guide the founder to define:

  1. Cohort grouping — How new users are grouped

    • Weekly: daily-use products
    • Monthly: utility products
    • Quarterly: infrequent-use products (travel, tax)
  2. Active action — What counts as "active." Must reflect genuine value delivery.

    • Ask: "Imagine watching a customer use your product. What moment tells you they're genuinely getting value?"
    • B2B SaaS: "completed a core workflow"
    • Consumer: "engaged with 3+ pieces of content"
    • Marketplace: "completed a transaction"
  3. Time granularity — How often users should ideally use the product. Cross-check against chosen action for consistency.

Triangle Chart (Cohort Retention Table)

         Week 0  Week 1  Week 2  Week 3  Week 4  Week 5
Jan      100%    62%     45%     38%     35%     34%   <- flattening
Feb      100%    58%     41%     33%     31%     ...
Mar      100%    65%     50%     42%     ...
Apr      100%    71%     55%     ...                    <- improving

Curve Shape Analysis (Most Important Insight)

Analyze SHAPE, not absolute numbers:

Curve Shape PMF Signal Agent Action
Flattening (stabilizes at any level) PMF detected Shift to growth Drivers. "Retention flattening at ~34%. Even Google Photos flattened at 20-40%."
Declining to zero (no stabilization) No PMF Shift to product/activation Drivers. Trigger WHY analysis. "Users not sticking. Understand why before investing in growth."
Rising (curves go up over time) Strong PMF + network effects Propose aggressive scaling. "Retention increasing — extremely strong signal."
Newer cohorts better Product improving "Product improvements working — newer cohorts retain better."
Newer cohorts worse Product or acquisition degrading "Warning: newer cohorts retain worse. Investigate product quality or acquisition quality."

Read the full file on GitHub · 108 lines

Changes

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.

  1. 10d ago First seen · 108 lines · 78 tokens per session scan A 7421f54d273a

Subscribe to this mod's changes

retention-cohorts is a skill published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 1,325 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

choice-architecture

Nudge-based choice architecture for 3-option selection UI — smart default vs active choice, outcome mapping, channel factors, RECAP, operational transparency with source attribution, post-decision reinforcement, error-forgiving undo, peak-end session design, user contribution acknowledgment. Use when presenting…

Ingramradical235/anty-framework · 72 tokens

failure-essence

4 strategic failure patterns from Essence of Failure — dual-objective trap (conflict stress test), strategic ambiguity (operationalizability test), withdrawal decision protocol (pre-committed stop conditions, re-present biweekly), assumption provenance auditing (source, verification, load-bearing flag, sample size).…

Ingramradical235/anty-framework · 79 tokens

pipeline

Cash Machine 10-step B2B sales pipeline with 3 presets, verifiable checkpoints per step, trajectory logging, bottleneck detection with utilization formula, lead qualification gate (BANT 6-criteria), pipeline velocity and stall detection (2x threshold), two-tier probability scoring, BBS tracking, end-of-quarter…

Ingramradical235/anty-framework · 84 tokens

plan-b

Plan B framework — 6 environmental forces monitoring, pre-mortem 5-step process, scenario planning with auto-trigger points, Devil's Advocate on every proposal, 100-day gate reviews, S-curve awareness, 5 hurdles to Plan B execution, boomerang prevention. Use when preparing contingencies, monitoring environmental…

Ingramradical235/anty-framework · 80 tokens

quest-interview

QUEST Socratic interview methodology — beginner stance, empathic neutrality, downward/upward questioning, echo questions, concept identification, permission checks, critical point pursuit, anti-pattern safeguards, resolution imbalance diagnostic, workaround discovery, painkiller vs vitamin test, locally famous test.…

Ingramradical235/anty-framework · 74 tokens

review-engine

5-question review framework (result, execution, plan, strategy, analysis), KPI propagation monitoring with 4-layer anomaly patterns, One-Way/Two-Way Door classification, withdrawal decision protocol, and assumption provenance auditing. Use during periodic reviews, buffer zone changes, or when evaluating why results…

Ingramradical235/anty-framework · 66 tokens