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-workspacegit 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-workspace)<a href="https://agentmods.dev/skills/eliasstravik/gtm-skills/gtm-workspace"><img src="https://agentmods.dev/badge/skills/eliasstravik/gtm-skills/gtm-workspace/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-workspace"><img src="https://agentmods.dev/badge/skills/eliasstravik/gtm-skills/gtm-workspace.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 | $0.00071 | $0.01368 |
| Opus 5 | $0.00036 | $0.00684 |
| Sonnet 5 | $0.00014 | $0.00274 |
| Haiku 4.5 | $0.00007 | $0.00137 |
Grade A, and why
gtm-workspace 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 today.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTM Workspace
Trigger
Apply this Lifecycle SOP when the requested outcome creates, imports, maintains, validates, repairs, or retires the GTM workspace itself.
Scope
Own the plain-Markdown workspace at ~/.gtm/<org-slug>/ across creation, import, organization and member maintenance, legacy-shape migration, structural or Git repair, and deletion. Create and fully research ORG.md artifacts with the shared company-data contract and MEMBER.md artifacts with the shared person-data contract. Preserve node-owned ICP and persona artifacts without authoring or validating their contents.
Contract
| Field | Public contract |
|---|---|
| Reads | The user's accepted organization facts, repository connection rules, valid local workspaces, and safe supplied sources |
| Writes | Workspace contract files, organization nodes, member files, repository configuration, and accepted structural repairs |
| Outputs | The requested workspace state summarized by display name and owner chain, a complete health report, or a fixed-connection refusal |
| Approval | The agent prepares, stages, inspects, and commits locally, then the user approves one plain-language card immediately before the push; whole-workspace deletion keeps its typed confirmation |
| Persists | Accepted workspace files and configuration in main Git history; no hidden coordination state |
| Handoff | gtm-icp for market definitions, gtm-persona for buyer definitions, and gtm-workflow for saved workflows |
Inputs
Use the user's request and accepted facts, the hosting environment's repo connection and durable-write declarations, valid local workspaces, and safe supplied sources.
Roles
The agent owns the selected lifecycle flow. The user approves one plain-language card immediately before the push that saves the prepared local commit; whole-workspace deletion keeps its typed confirmation. The hosting environment declares fixed connections.
Procedure
| Condition | Owned flow |
|---|---|
| A fixed-connection deployment receives import, sharing setup, whole-workspace deletion, a create for a repo other than the connected one, or another connection-changing request | Refuse and redirect through the surface-refusal flow; perform nothing for that request |
Create is requested on a fixed-connection deployment whose connected repo has no root ORG.md or legacy org.md |
Guide the create flow with its connected-repo substitutions; the first saved change writes ORG.md together with the contract files |
| No lifecycle verb is clear | Guide the lifecycle menu and retain ownership of the selected flow |
| Create is requested | Send one intake decision message, research every supplied source, prepare one local commit for the organization and every supplied suborganization and member, show one card, push once on approval, then close |
| Import is requested | Guide a local copy or GitHub clone through inventory, accepted conversion, history, optional sharing, and summary |
| Update is requested | Resolve the target, describe the changed facts, save the accepted changes, and close |
| Delete is requested | Resolve the target, describe consequences, obtain the required confirmation, delete, and explain recovery where available |
| Doctor or migration is requested, or the workspace seems wrong | Run every contract, legacy-shape, and Git check; describe accepted repairs or migrations; save one change set; and report complete health |
What ships with it
10 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.
- today Changed 5f5119f04c4c
- yesterday Changed a9d29e99d19c
- 3d ago Changed · +1 lines 35f45c300dd5
- 8d ago Changed · +1 lines 3157afe4f1d4
- 12d ago First seen · 71 lines · 71 tokens per session scan A b3a27c7b382e
gtm-workspace is a skill published in the GitHub repository eliasstravik/gtm-skills (12 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,368 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
session-relay
Maintain lightweight project continuity for long GTM Brain builds by keeping a relay README as the source of truth, archiving transcript links without reading them by default, and producing concise handoff prompts.
client-onboarding
Use when a deal closed or a user signed up and the first 30 days need an activation plan: sales→delivery handoff, one verifiable activation event, kickoff, and a 30/60/90 or day-0→14 plan with owners, dates and a measurable exit. NOT reactive ticket triage (that is customer-support), NOT renewals/churn past the…
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.
co-founder-dynamics
Complete co-founder playbook for technical founders — finding co-founders, equity splits (dynamic and static), co-founder agreements, vesting schedules, working relationships, conflict resolution, co-founder breakups, and the "dating before marrying" framework. Use when looking for a co-founder, structuring a founding…
kill-the-standup
Reads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing / blockers), and posts it to Slack. Use when asked to write a standup, generate a standup update, post to the standup channel, summarize yesterday's work, or automate the daily standup. Trigger when a…
support-tool-stack
Customer support platform selection, setup, and optimization — Intercom, Zendesk, Front, Help Scout, HubSpot Service Hub, Linear, and AI-native tools. Use when choosing a support platform, migrating tools, setting up help desk workflows, designing ticket routing, building macros and saved replies, or integrating…