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 01-strategy-and-roadmapgit 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/01-strategy-and-roadmap)<a href="https://agentmods.dev/skills/aidevgtm/gtm-cofounder/01-strategy-and-roadmap"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/01-strategy-and-roadmap/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/01-strategy-and-roadmap"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/01-strategy-and-roadmap.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 | $0.00097 | $0.01571 |
| Opus 5 | $0.00048 | $0.00785 |
| Sonnet 5 | $0.00019 | $0.00314 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
strategy-and-roadmap 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategy and roadmap (your plan)
A pile of tactics is not a go-to-market. This turns your brief into a diagnosis and a prioritized plan, and becomes the one place you come back to when you don't know what to do next.
Use this when: you've done the brief and don't want to guess which skill to pull, or a chat ended and you're staring at "what now," or you keep getting handed standalone tasks (do the homepage, make a content plan) that don't add up to a strategy.
The core idea
The other skills are moves. This is the game plan that decides which move, and when. It does three things:
- Diagnose. Read the brief honestly. Where are you actually strong? What is the single biggest thing standing between you and your next 10 users or your first dollar? Name one bottleneck, not five.
- Prioritize by stage. The right first move for a founder with zero users is not the right first move for one with 500 users and no revenue. Sequence the work to the stage you're actually at, and say out loud what to ignore for now.
- Persist. Write it to
docs/gtm-cofounder/gtm-roadmap.mdso it survives the chat. Next session you read the roadmap, not a dead thread.
How to run this (for the agent)
- Read
docs/gtm-cofounder/founder-brief.mdfirst. If it does not exist, runstart-herebefore this. Everything here keys off the brief. - Lead with a diagnosis, not a task list. Two or three sentences: here is what's working, here is the one bottleneck that matters most right now, and here is why.
- Be willing to tell them to do almost nothing. If most of the brief is
[assumption]and they've barely spoken to users, the honest roadmap is short: go talk to 10 users, come back. Do not pad it to look thorough. - Sequence into three horizons: Now (the one thing), Next (the two or three that follow), Later (parked on purpose, so it's off their mind). Map each item to a skill.
- Offer, never impose. Present the roadmap and ask what they want to start with. Do not assign or begin a task they have not chosen. If they say no to something, move it to Later and drop it, do not resurface it next turn.
- Write the plan, not a copy of the brief.
docs/gtm-cofounder/gtm-roadmap.mdis a separate, different document fromdocs/gtm-cofounder/founder-brief.md. The brief is the context; the roadmap is the short, decision-shaped plan you derive from it. Never re-save the brief's contents into the roadmap. Ifdocs/gtm-cofounder/gtm-roadmap.mddoes not open with a one-line Diagnosis followed by Now / Next / Later, it is wrong.
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 · 77 lines · 97 tokens per session scan A 9f4fdf00dc73
strategy-and-roadmap is a skill published in the GitHub repository AIDevGTM/gtm-cofounder (274 stars, last pushed 4d ago), licensed MIT. It adds 97 tokens to every session and 1,571 once invoked, about $0.0005 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…