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 AIDevGTM/gtm-cofounder --skill 00-start-heregit clone --depth 1 https://github.com/AIDevGTM/gtm-cofounderWrote 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/aidevgtm/gtm-cofounder/00-start-here)<a href="https://agentmods.dev/skills/aidevgtm/gtm-cofounder/00-start-here"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/00-start-here/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/aidevgtm/gtm-cofounder/00-start-here"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/00-start-here.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.02124 |
| Opus 5 | $0.00038 | $0.01062 |
| Sonnet 5 | $0.00015 | $0.00425 |
| Haiku 4.5 | $0.00008 | $0.00212 |
Grade A, and why
start-here 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start here (your founder brief)
Every other skill is only as sharp as what the agent knows about your business. This is that context. Do it once, and every skill after it gets personal.
Use this when: it's your first time here, or the advice you're getting feels generic and textbook because the agent doesn't actually know your product, your users, or your stage.
The core idea
Answer five core questions and the agent writes a docs/gtm-cofounder/founder-brief.md in your project, enough to give you a real diagnosis and a roadmap in minutes. Everything else is optional and answered as you go: each skill pulls the deeper questions it actually needs, when it needs them, and tells you what answering unlocks. So you start seeing value fast, and the brief gets richer the more you use it, instead of facing a wall of questions on day one.
And the part that matters most: separate what you have validated (a real user who is not your friend told you) from what you are assuming (your best guess for now). Assumptions are completely fine to start with. They just get sent to talk-to-users to become real, so you never build a beautiful go-to-market on a guess.
How to run this (for the agent)
- Ask the five core questions one at a time, and nothing else. One question, wait for the answer, let it shape the next. It should feel like a conversation with a co-founder, not a form to fill in. Never paste multiple questions at once. (If the founder would rather see all five and answer in one go, give them the list, but default to one at a time.)
- Write the brief from those five, then move to
strategy-and-roadmap. The founder should get a diagnosis and a next move before they answer anything optional. - Pull the deeper questions just-in-time. When a later skill needs more (positioning needs the villain, pricing needs the buyer), ask only the two or three relevant ones right then, and say what answering unlocks. Never front-load them.
- For every substantive answer, ask: "have you heard a real user say this, or is that your read for now?" Tag it
[validated]or[assumption]. - "Zero users interviewed" is a valid and revealing answer. Note it plainly, no judgment, and flag
talk-to-usersas the highest-priority next step. - Keep the founder's own words. Don't polish their pain into marketing language.
- Once the core brief is written, do not jump into a task or start prescribing work. Hand off to
strategy-and-roadmap, or ask the founder what they want to tackle. Offer, never impose.
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 · 102 lines · 76 tokens per session scan A f0fa6b9fed06
start-here is a skill published in the GitHub repository AIDevGTM/gtm-cofounder (274 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 2,124 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 2026-08-30.
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]"…
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…
github-actions-trigger
Trigger GitHub Actions workflows from Claude Code. Auto-run tests, deploy, or validate when skills like run-pre-commit-checks complete.
screenshot-automation
Automatically captures, crops, and beautifies screenshots from URLs for your portfolio or docs.
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…
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…