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 03-talk-to-usersgit 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/03-talk-to-users)<a href="https://agentmods.dev/skills/aidevgtm/gtm-cofounder/03-talk-to-users"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/03-talk-to-users/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/03-talk-to-users"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/03-talk-to-users.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 | $0.00052 | $0.01034 |
| Opus 5 | $0.00026 | $0.00517 |
| Sonnet 5 | $0.00010 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
talk-to-users 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talk to users (the TAB system)
The best marketing to developers comes from talking to developers. That's it. Everything else in this repo is downstream of this skill.
Use this when: you've never done a real user interview, your messaging is clever but unverified, or you keep debating the roadmap internally instead of asking the people who feel the pain.
The core idea
Stand up a Technical Advisory Board: 30-50 people who represent your users and buyers, not grey-haired advisors telling you how to build. You interview them, on repeat, and let their words become your positioning, roadmap, and homepage copy.
A TAB call is not a demo and not a sales call. It's an interview. You never mention the product.
Framework: the TAB system (Frankl)
Composition
- One+ representative of every persona that touches the product (see
who-is-this-for) - Both users (interact) and customers (pay), often different people
- Target 30-50 members
Cadence
- 30 minutes · one-on-one · monthly · for ~6 months
- Zoom, recorded with permission, never in person
- Same questions every time · never pitch
Recruitment (it's a numbers game)
- Personalize every message, never batch-and-blast
- Lead with their problem, not your startup
- Max 4 sentences
- ~10% reply → plan ~500 outreaches for ~50 members
- No payment: early access, influence, swag
Template:
Dear [Name],
Your post about [specific problem] was genuinely sharp.
I'm building something to attack [that problem] and I'd value your view. Would
you consider joining my technical advisory board?
If so, reply and I'll set up a short call to explain what's involved.
The 7 questions (never more than 7 in 30 min)
- Magic wand: "If you could wave a magic wand and change anything about how you do [task], what would it be?"
- The stakes: "If we delivered that, how would it change your day / your work?"
- Why now: "What's different about the world now that makes this more valuable than five years ago?"
- What caused this problem in your org?
- What have you tried, and why did it fall short?
- What happens if nothing changes for another year?
- Where do you go to stay current on this? (who/what they trust)
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.
- 12d ago First seen · 91 lines · 52 tokens per session scan A cf74dd00aeff
talk-to-users is a skill published in the GitHub repository AIDevGTM/gtm-cofounder (276 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 1,034 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.
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]"…
github-actions-trigger
Trigger GitHub Actions workflows from Claude Code. Auto-run tests, deploy, or validate when skills like run-pre-commit-checks complete.
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…
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…