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 eliasstravik/gtm-skills --skill gtm-get-startedgit clone --depth 1 https://github.com/eliasstravik/gtm-skillsWrote 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/eliasstravik/gtm-skills/gtm-get-started)<a href="https://agentmods.dev/skills/eliasstravik/gtm-skills/gtm-get-started"><img src="https://agentmods.dev/badge/skills/eliasstravik/gtm-skills/gtm-get-started/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/eliasstravik/gtm-skills/gtm-get-started"><img src="https://agentmods.dev/badge/skills/eliasstravik/gtm-skills/gtm-get-started.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00118 | $0.00917 |
| Opus 5.5 | $0.00047 | $0.00367 |
| Sonnet 5.5 | $0.00024 | $0.00183 |
| Haiku 4.5 | $0.00012 | $0.00092 |
Grade B, and why
gtm-get-started scanned grade B with 1 finding 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 yesterday.
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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
2. Say in one sentence what is already in place and what comes next, then hand off: load that skill (the host's skill tool, such as Skill, or read its `SKILL.md`) and follow its procedure for that job now. Never tell the How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTM Get Started
Trigger
Apply this skill when a request asks where to start or what to do next with GTM Skills and names no job.
Scope
A guide: it reads the workspace, finds the next step, and hands that step to the gtm skill that owns it in the same conversation, then checks again. It never writes a file itself; every write is the owning skill's job.
Inputs
The request; the workspace found by the discovery order in the contract; its icps/*/ICP.md and personas/*/PERSONA.md.
Roles
The user answers the owning skill's questions and picks the goal when the foundations are done; the agent reads, hands off, and carries on.
Procedure
The first gtm skill used in a conversation checks once for a newer release, as updates says. Talk by the six rules in interaction; reproduce the dialogues.
- Take the first row whose check holds:
| Check | Hand off to |
|---|---|
| No workspace found | gtm-workspace, Create: the organization's workspace |
| No ICP | gtm-icp, Create: the companies to sell to |
| No persona | gtm-persona, Create: the people to sell to |
| All three exist | Ask What next? with Check a company or person now (Recommended) → gtm-qualify-prospects, Check them on a schedule → gtm-workflow, Use it in Slack → gtm-agent |
- Say in one sentence what is already in place and what comes next, then hand off: load that skill (the host's skill tool, such as Skill, or read its
SKILL.md) and follow its procedure for that job now. Never tell the user to say a phrase or run a slash command to start it. Ask only what the owning skill needs, such as the company name when the request names none. - When the owning skill closes its save, go back to step 1 and continue. After the user's pick in the last row, that skill's job is the rest of the conversation.
Outputs
The missing foundations made by their own skills in one conversation, then the chosen skill's job; get-started itself writes no files.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed 03364304ec2f
- 2d ago Changed e0c9c9649d98
- 9d ago Changed 35c6e2d1ad9b
- 16d ago Changed · +1 lines · +4 tokens per session scan A → B 7ffd53b77ea6
- 17d ago First seen · 57 lines · 114 tokens per session scan A 7a04dbfe1839
gtm-get-started is a skill published in the GitHub repository eliasstravik/gtm-skills (19 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 917 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.
Other skills, from other repositories
startup-launch-playbook
A step-by-step playbook for early-stage startups going from pre-seed to their first 1000 users. Covers MVP validation, initial traction channels, and founder-led growth tactics. By @WeiYipei — follow on X for more startup growth insights.
content-atomizer
Repurposes single content pieces into multiple formats for maximum distribution while maintaining brand voice. This skill should be used when maximizing ROI from pillar content, filling content calendars efficiently, reaching audiences across multiple platforms, or when creating original content for every channel…
orchestrator
Diagnoses marketing needs and sequences appropriate skills for comprehensive campaigns. This skill should be used when unsure which marketing skill to use, planning multi-step marketing campaigns, creating integrated marketing strategies, or when a project spans multiple marketing disciplines.
sales-orchestrator
Diagnoses sales needs and sequences appropriate skills for comprehensive deal execution. Use this skill when unsure which sales skill to use, planning multi-step deal strategies, coaching reps on process, or coordinating complex sales motions.
google-tag-manager
Skill "google-tag-manager" from VKirill/claude-lane-stack, covering 🎯 version requirements (june 2026), usage, use this skill when, do not use this skill when and purpose.
keyword-research
Content planning framework using the 6 Circles Method for identifying high-value topics without paid SEO tools. This skill should be used when building content strategy from scratch, planning quarterly content calendars, finding content gaps, or when unsure what to write about next.