Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/localplugins/pluginsnpx agentmods add skills/localplugins/plugins/generate-socialWrote 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/localplugins/plugins/generate-social)<a href="https://agentmods.dev/skills/localplugins/plugins/generate-social"><img src="https://agentmods.dev/badge/skills/localplugins/plugins/generate-social/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/localplugins/plugins/generate-social"><img src="https://agentmods.dev/badge/skills/localplugins/plugins/generate-social.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 | $0.00093 | $0.01289 |
| Opus 5.5 | $0.00037 | $0.00516 |
| Sonnet 5.5 | $0.00019 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
generate-social 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 1mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Social
Generates a platform-sized, on-brand social template as SVG from the active brand profile, with editable text zones the user can tweak afterward.
Overview
The generate-social skill turns a headline (and optional subhead and call-to-action)
into a correctly sized social graphic that uses the brand's palette and fonts. Output
is vector SVG, so it scales cleanly and needs no account, key, or network call. The
generator (lib/social.mjs) lays out a brand band, a wrapped headline, an optional
subhead, and an optional accent pill; the skill resolves the active profile, picks the
platform, runs the generator, and saves the file. For a photographic background behind
the template, the raster path lives in the generate-graphic skill.
Prerequisites
- An active brand profile created with
/brand-new(abrand/directory, orbrands/[slug]/). Read loads itscolor-system.jsonandtypography.json. - Node.js on the PATH — the generator runs as
node lib/social.mjs. - Write access to an
output/directory in the working repository. - A headline string; subhead and call-to-action are optional parameters.
Instructions
-
Run
/brand-statusto confirm the active brand; if none exists, tell the user to run/brand-newand stop. -
Use Glob to locate the active brand directory, then Read and validate the profile with
validateProfile. Stop with the offending field if validation fails. -
Choose the platform preset —
instagram-square(default),instagram-story,og-card, oryoutube-thumb. Ask the user when unspecified. -
Generate the template by running the node generator:
import { loadProfile } from '../../lib/brand.mjs'; import { buildSocial } from '../../lib/social.mjs'; const profile = loadProfile(activeDir); const { svg, platform } = buildSocial(profile, { platform: 'instagram-square', headline: 'We just raised our Series A', subhead: 'Building the future of logistics', cta: 'Read the story', });
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.
- 1mo ago First seen · 119 lines · 93 tokens per session scan A ab6dc5df192f
generate-social is a skill published in the GitHub repository localplugins/plugins (5 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 1,289 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
customer-journey-map
Create an end-to-end customer journey map with stages, touchpoints, emotions, pain points, and opportunities. Use when mapping the customer experience, identifying friction points, improving onboarding, or visualizing the user journey.
visual-explainer
Generate self-contained HTML pages that visually explain technical material — systems, code changes, plans, data. Use when the user asks for any diagram or visual explanation, when they want a slide deck or a longform document (user guide, how-to, reference page), when another skill needs one rendered, or proactively…
assets-redes-sociais
Templates e especificações para redes sociais: feed, stories, banners e thumbnails.
verifying-design-canvas
Verify a live deployed app matches its Claude Design canvas (.dc.html): theme tokens, DOM/a11y structure, every interactive state — not just default view. Building instead of verifying? See artifact-design.
brand
A project-specific visual identity for chat cards and saved reports, using the project's colors, logo, and fonts. It finds these details in the repository or asks the user for them, then stores the result in a committable `.readable/` folder.
auditing-website-accessibility
Audits website accessibility for WCAG 2.2 AA compliance, generating findings and code fixes. Use when reviewing accessibility, keyboard navigation, screen reader compatibility, or inclusive design.