know-if-its-working

know-if-its-working is a skill for Claude Code from AIDevGTM/gtm-cofounder. It costs 59 tokens per session (981 once invoked), scanned A, original, MIT.

A measurement framework for checking whether developer-focused marketing and sales are working, using retention and funnel metrics instead of surface numbers such as pageviews or repository stars.

In plain words
What is it for?
Use it to measure returning developer cohorts, track stages from discovery through adoption, and choose one meaningful metric for each stage.
Why use it?
It reveals when new users are leaving, so teams do not keep acquiring people into a product that fails to retain them.

Skill for Claude Code

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

Part of the gtm-cofounder plugin — 19 skills shipped together

Good fit Use it to measure returning developer cohorts, track stages from discovery through adoption, and choose one meaningful metric for each stage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aidevgtm/gtm-cofounder/15-know-if-its-working
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 AIDevGTM/gtm-cofounder --skill 15-know-if-its-working
Clone the repo
git clone --depth 1 https://github.com/AIDevGTM/gtm-cofounder

Made for: Claude Code.

Or install gtm-cofounder, the plugin that ships this one along with the rest of its 19 skills.

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 know-if-its-working

README.md
[![agentmods](https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/15-know-if-its-working/github.svg)](https://agentmods.dev/skills/aidevgtm/gtm-cofounder/15-know-if-its-working)
Your own site
<a href="https://agentmods.dev/skills/aidevgtm/gtm-cofounder/15-know-if-its-working"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/15-know-if-its-working/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 know-if-its-working

Your own site · 80×15
<a href="https://agentmods.dev/skills/aidevgtm/gtm-cofounder/15-know-if-its-working"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/15-know-if-its-working.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 981 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00059 $0.00981
Opus 5 $0.00030 $0.00491
Sonnet 5 $0.00012 $0.00196
Haiku 4.5 $0.00006 $0.00098

Measured 12d ago against content hash 6b380d51b3eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

know-if-its-working 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 12d 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.

skills/15-know-if-its-working/SKILL.md · 78 lines

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.

Know if it's working

The only early metric that matters is net developer retention. Without it, you're not running a funnel; you're running a colander.

Use this when: you're tracking GitHub stars and pageviews and still can't answer "is GTM working?", or you're pouring effort into acquisition while new users quietly churn.

The core idea

Acquisition is worthless if users don't come back. Prove retention first; only then does spending on acquisition make sense. Most early founders optimize the top of the funnel while the bottom leaks. Fix that order.

Framework: net developer retention (Frankl)

Of all the developers who first used the product in Month 1, how many used it in Month 2? Month 3?

  • Hold it above 100% (meaning existing cohorts grow through internal referral/expansion).
  • Below solid retention, do not focus on acquisition: you're filling a leaky bucket.
  • This single cohort question tells you more than every vanity chart combined.

Framework: the DREAM metrics (Frankl)

Measure one honest number per stage, not pageviews, not stars.

Stage The metric that counts
Discovery unique human visitors / month
Research newsletter subs + community joins + follows
Evaluation free-tier signups / downloads / active free users
Activation monthly active users · frequency · session depth
Membership community members actively posting & answering

The gate before all of it, the weekend test: can a new developer get to first value over a weekend from docs + Stack Overflow, no support call? Time-to-value target: < 1 hour ideal, 1 day max. If Evaluation/Activation fails here, no channel work will save you.

Growth benchmarks (non-ARR, Frankl)

  • Pre-seed: ~30% month-over-month user growth
  • Post-Series-A: ~10% MoM
  • First $1M ARR: within 12 months is good, 9 is excellent

Framework: attribution philosophy (Czakon)

Developer marketing is hard to attribute and that's normal. A dev sees your HN post, reads a tutorial, lurks for two months, then signs up direct.

  • Don't over-trust last-touch; it will tell you "direct/organic" and hide the real work.
  • Add a "how did you hear about us?" free-text field. Self-reported attribution beats a broken model.
  • Judge channels on trend and directional signal, not spurious precision.

Read the full file on GitHub · 78 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. 12d ago First seen · 78 lines · 59 tokens per session scan A 6b380d51b3eb

Subscribe to this mod's changes

know-if-its-working is a skill published in the GitHub repository AIDevGTM/gtm-cofounder (276 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 981 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

git-phase-restore

Autonomous Git-based project phase restoration. Uses Git history (commits, tags, branches, diffs, semantic messages) to identify and restore any development phase automatically. Trigger for: "restore to when X worked", "go back to before Y broke", "show project phases", "undo the last feature", "roll back to [phase]"…

mahmoud20138/Tradecraft · 165 tokens

e2b-sandboxes

E2B open-source cloud sandboxes for executing AI-generated code securely. USE FOR: run code in sandbox, e2b, code interpreter, execute AI code, secure code execution, isolated environment, AI coding agent execution, run untrusted code, cloud sandbox, code execution API, python sandbox cloud, AI agent code runner, safe…

mahmoud20138/Tradecraft · 82 tokens

github-actions-trigger

Trigger GitHub Actions workflows from Claude Code. Auto-run tests, deploy, or validate when skills like run-pre-commit-checks complete.

mahmoud20138/Tradecraft · 32 tokens

screenshot-automation

Automatically captures, crops, and beautifies screenshots from URLs for your portfolio or docs.

akhilkannur/marketing-agent-blueprints · 22 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

google-ads-audit

Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…

nowork-studio/notfair-plugin · 86 tokens