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 swan-gtm/gtm-skills --skill visual-argument-reviewgit clone --depth 1 https://github.com/swan-gtm/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/swan-gtm/gtm-skills/visual-argument-review)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/visual-argument-review"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/visual-argument-review/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/swan-gtm/gtm-skills/visual-argument-review"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/visual-argument-review.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 Excessive Agency · line 45 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00122 | $0.01225 |
| Opus 5 | $0.00061 | $0.00613 |
| Sonnet 5 | $0.00024 | $0.00245 |
| Haiku 4.5 | $0.00012 | $0.00122 |
Grade A, and why
visual-argument-review 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Applies when a finished or near-finished marketing asset needs a critical read before it reaches a buyer, partner, or client. Produces a prioritized, fixable design read, not a vibe check.
Review it the way a senior B2B designer would, not a generic assistant. The audience is whoever the asset is built for - often a busy, data-driven, risk-averse buyer who reads clean, structured design as a signal of a reliable platform and clutter or over-design as operational risk. Anchor the review on that specific reader. The reviewer's job is to make the asset accelerate a business decision.
The lens
One idea governs the whole review: design is the visual architecture of an argument, not a layer of polish on top of text. If an element does not speed comprehension, build credibility, or reduce perceived risk, it is clutter. Competent designers add; strong ones remove. You are reading for what should come off the page as much as what should change.
Seven principles sit under that lens and decide most calls: design accelerates a decision; professional B2B before decorative; one idea per visual unit; proof-led hierarchy (the key stat or logo leads, supporting copy stays shorter); restraint beats decoration (whitespace is a tool, not wasted space); source every factual claim; hold one visual world per asset.
Run the review across eight dimensions
Read the asset against eight dimensions, in this order, so the structural problems surface before the cosmetic ones. Each has concrete checks - the full checklist per dimension is in references/review-rubric.md.
- Strategic fit - who it is for and what decision it should move; does the hierarchy lead with the right proof for that audience.
- Brand fidelity - correct palette, logo, type, and one visual world; no near-match colors.
- Story and hierarchy - one message per unit, action titles not labels, a ten-second scan reveals the argument.
- Layout craft - grid alignment, consistent margins and repeated positions, roughly a third of the canvas breathing.
- Typography craft - a clear type scale, equivalent elements at equivalent sizes, readable at the real destination size, no overflow or orphans.
- Proof and data design - metrics real, sourced, and labelled; number first, label second; charts with units and sources; no 3D or misleading charts.
- Imagery and assets - real, sharp screenshots in the right orientation; device frames keep aspect ratio; logos at even weight; icons from one consistent set.
- Polish and client-readiness - would you send this to a top client without flinching; does it read as an intentional system, not a filled-in template.
What ships with it
3 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 · 55 lines · 122 tokens per session scan A 2b3ae3250a91
visual-argument-review is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 122 tokens to every session and 1,225 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
open-design-landing-deck
OpenDesign's brand-story deck for partners and press: why it exists, what it believes, and where design is going. Built as a decision-grade marketing & GTM deck for partners, press, community.
fs-emerald-editorial
OpenDesign's 'design on your desk' brand-launch narrative: the market moment, the story, and the proof that converts. Built as a decision-grade marketing & GTM deck for marketing team, press.
huashu-pentagram-grid
OpenDesign's positioning & messaging system: the one-line promise, the pillars, and the proof — the source of truth for all copy. Built as a decision-grade marketing & GTM deck for brand & marketing team.
saas-landing
A single-page SaaS landing page for a software product, with sections such as the hero, features, customer proof, pricing, FAQs, and a call to action. SaaS means software delivered online, usually by subscription.
app-icon-optimization
When the user wants to design, test, or improve their app icon to increase tap-through rate and conversions in App Store search and browse. Use when the user mentions "app icon", "icon design", "icon A/B test", "icon variants", "tap-through rate", "icon conversion", "icon refresh", or wants to know what makes a good…
screenshot-optimization
When the user wants to design, optimize, or evaluate App Store screenshots and preview videos. Also use when the user mentions "screenshots", "app preview", "product page design", "screenshot design", "creative assets", or "what should my screenshots show". For A/B testing screenshots, see ab-test-store-listing. For…