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-personagit 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-persona)<a href="https://agentmods.dev/skills/eliasstravik/gtm-skills/gtm-persona"><img src="https://agentmods.dev/badge/skills/eliasstravik/gtm-skills/gtm-persona/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-persona"><img src="https://agentmods.dev/badge/skills/eliasstravik/gtm-skills/gtm-persona.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 | $0.00128 | $0.01004 |
| Opus 5.5 | $0.00051 | $0.00402 |
| Sonnet 5.5 | $0.00026 | $0.00201 |
| Haiku 4.5 | $0.00013 | $0.00100 |
Grade A, and why
gtm-persona 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 22d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTM Persona
Trigger
Apply this skill when a request creates, changes, removes, or checks a persona in a GTM workspace.
Scope
This skill owns personas/<slug>/PERSONA.md in the workspace found by the contract. A persona records desired or accepted criteria for target people in the 11 fields of person data, never facts about the organization or its members.
Inputs
Criteria from the user or sources the user supplies; the existing personas, for the near-duplicate check; the workflows that read this persona (readPersona("<slug>") in workflows/workflows/*.ts), for the workflow notice.
Roles
The user approves every change through the host's write permission; the agent proposes, edits, commits, and reports.
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.
| Job | Do |
|---|---|
| Create | When an existing persona overlaps the request, offer Update first. When the titles that define the persona are unstated, ask with options. Copy templates/PERSONA.md to personas/<slug>/PERSONA.md, fill only the criteria the user gave, leave the rest Unknown, and say the rest stays Unknown because criteria are never borrowed from the company record or members. Omit ## Person signals and ## Disqualifiers when empty. |
| Update | Change the named criteria, signals, or disqualifiers. When a workflow reads this persona, say its next run uses the change (a deployed copy once this push has deployed) and rows it already scored keep their scores until they are rescored. |
| Delete | When no persona has the given name, offer the closest matches as options. Say whether a workflow reads it: that workflow's runs fail until it names another persona. Remove personas/<slug>/; close with what disappeared and that it stays in the workspace's history. |
| Doctor | Flag a persona with no person-matchable criterion (every field Unknown), a placeholder husk, a missing H1, or a folder name that is not its slug; offer the fixes as options; rewrite what the user accepts. |
What ships with it
2 files 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.
- 22d ago Changed 51d1de8d5b40
- 23d ago Changed 2799c9427981
- 1mo ago Changed 39c31bed59e8
- 1mo ago Changed a44b09f50fb3
- 1mo ago Changed 466b450ce354
- 1mo ago Changed · +2 lines dd52d4e0636d
- 1mo ago Changed · -15 lines · +45 tokens per session bded5f5c16cc
- 1mo ago Changed e8001534bb8b
- 1mo ago Changed 3e572d149516
- 1mo ago First seen · 69 lines · 83 tokens per session scan A 42f126056985
gtm-persona is a skill published in the GitHub repository eliasstravik/gtm-skills (24 stars, last pushed 22d ago), licensed MIT. It adds 128 tokens to every session and 1,004 once invoked, about $0.0005 per session on Opus 5.5. 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.
gtm-persona compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gtm-personaeliasstravik/gtm-skills | Skill | 24 | 22d ago | MIT | A | 128 | Claude Code, Codex |
| startup-launch-playbookGingiris-1031/gingiris-skills | Skill | 89 | 2d ago | MIT | A | 58 | Claude Code, Codex |
| google-tag-managerVKirill/claude-lane-stack | Skill | 124 | 8d ago | MIT | A | 134 | Claude Code |
| content-atomizerSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 57 | Claude Code |
| orchestratorSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 49 | Claude Code |
| sales-orchestratorSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 46 | Claude Code |
| keyword-researchSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 54 | Claude Code |