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 octavehq/lfgtm --skill traingit clone --depth 1 https://github.com/octavehq/lfgtmWrote 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/octavehq/lfgtm/train)<a href="https://agentmods.dev/skills/octavehq/lfgtm/train"><img src="https://agentmods.dev/badge/skills/octavehq/lfgtm/train/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/octavehq/lfgtm/train"><img src="https://agentmods.dev/badge/skills/octavehq/lfgtm/train.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 202 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00109 | $0.05133 |
| Opus 5 | $0.00055 | $0.02567 |
| Sonnet 5 | $0.00022 | $0.01027 |
| Haiku 4.5 | $0.00011 | $0.00513 |
Grade A, and why
train 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 9d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/octave:train - Onboarding GTM Primer
Generate the one lesson a new rep completes on day one to learn how your company sells. The primer turns your Octave library into a self-contained, gated interactive slide lesson: five teaching topics, one per slide, each ending with checkpoint questions the rep must clear before Next unlocks, then a score. The topics are what we sell and the problem it solves, who we sell to, how to position to each buyer (an interactive per-persona selector), who we compete with and how we win (a tabbed competitor deep-dive), and the proof to point to (tabbed by lens).
This is a workspace-level, evergreen lesson, not an account plan. There is no target company. It is grounded entirely in the library's own GTM: the workspace company positioning, personas and segments, Motion ICP cell narratives, competitors, proof points, and references. The full spec, slide order, interaction model, and review checklist live in primer-sections.md.
On-brand styling — brand kit first, then generate
Resolve the brand before generating (do not skip this step). The primer is an internal enablement document for the workspace company's own team, so it goes out on the workspace company's brand (the Octave customer whose workspace you are operating in). There is no target account.
Step 1: Identify the workspace company. Call get_workspace_company to get the company name, domain/URL, and positioning. This is the company whose brand the primer uses and whose GTM it teaches.
Step 2: Resolve the workspace company's brand kit. Slugify the workspace company name AND its domain, and check for a cached brand kit at ~/.octave/brands/<slug>/manifest.json (try both slugs). If a complete kit exists (has manifest.json and tokens.css), use it automatically:
- inline the kit's
tokens.css(:root+ the embedded@font-face) and../get-brand-components/assets/kit_base.cssinto the output<style>; - follow the kit's
brand-kit.md→ Signature moves. - Use the kit's real logo, resolved dynamically (never hardcode a logo). The logo changes per company, so read it from the resolved kit's
manifest.jsonlogoblock. Use the onLight variant on light surfaces (the topbar over content slides) and the onDark / white variant on the dark gradient bands (cover, completion, and the topbar while those are showing). Inline the logo as a base64 data URI in the HTML so the file stays self-contained and survives sharing (do not reference a local file path in the delivered file). If the kit only has one logo variant, use it as-is on light and recolor to white for dark bands (filter: brightness(0) invert(1)) only as a fallback. - Verify the logo is actually the workspace company's mark before using it. Cached kits can contain a mislabeled or stray asset (a real example: the cached Octave kit's
*-logo-white.pngwas actually a WorkSpan logo). Open/preview the resolved logo file; if a variant is the wrong company or clearly wrong, use another variant, another cached kit for the same company, or recolor the known-good variant. Never ship a logo you have not eyeballed. If no complete kit exists → build one. Run theget-brand-componentsskill (read its SKILL.md and follow it) for the workspace company's domain, which captures the real logo among other assets. If the first attempt returns incomplete results, retry up to 3 times with different approaches (root domain,www.prefix,/aboutsubpage). Only fall back to a style preset after 3 genuine failures.
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.
- 9d ago First seen · 348 lines · 0 tokens per session scan A 3846bf39b903
train is a skill published in the GitHub repository octavehq/lfgtm (11 stars, last pushed 19d ago), licensed MIT. It adds 109 tokens to every session and 5,133 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.