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 tang-vu/social-posting-skills --skill image-generationgit clone --depth 1 https://github.com/tang-vu/social-posting-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/tang-vu/social-posting-skills/image-generation)<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/image-generation"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/image-generation/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/tang-vu/social-posting-skills/image-generation"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/image-generation.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 | $0.00023 | $0.00471 |
| Opus 5.5 | $0.00009 | $0.00188 |
| Sonnet 5.5 | $0.00005 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
image-generation 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.
What it actually says
Image / Media (Campaign Layer)
Campaign media is managed, not improvised: every asset enters via
campaign assets add with alt text and provenance, and validation checks
bounds per platform (platforms/*.json).
Discipline
- Assets are explicit:
campaign assets add <id> <file> --alt "..." --item <i> - Alt text is required for accessibility — describe what the image SHOWS (content and function), not keywords. Under ~125 chars where possible.
- Provenance matters: mark AI-generated images as such (Meta/FB require AI labels; honesty is the default everywhere).
- Never attach files with sensitive names/contents; the CLI refuses obvious ones (.env, keys, tokens) — don't try to work around it.
- Validate bounds before publishing: count, MB, format, aspect — the
validator reads
platforms/*.json; trust it over memory.
Size guidance
Recommended sizes live in each platforms/<id>.json (media.imageSize,
media.maxImageMB, media.formats). When generating an image, target the
platform's ratio: roughly 16:9 for X/Bluesky/LinkedIn link cards, 1:1 for
Threads, 5:3 for Product Hunt gallery, ~2.4:1 for Dev.to covers, tall or
square where the platform crops centrally.
What makes a good campaign image
- Shows the product working (screenshot, demo frame) > abstract art.
- One focal point, readable at feed size.
- Text overlay only when it survives small sizes; better in alt/title.
- Consistent with the post's claim — no fake screenshots, no fabricated charts. Media is evidence, not decoration.
Prompt patterns (for generation tools)
{subject}, {context}, flat illustration|isometric|clean product shot,
{palette}, minimal, no text overlay, high contrast for feed thumbnails
Keep prompts honest: don't generate "screenshots" of a UI that doesn't exist. For product shots prefer real captures via the media manifest.
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 Changed · -67 lines · +12 tokens per session e4b5191392b9
- 1mo ago First seen · 116 lines · 11 tokens per session scan A 91883c0501d2
image-generation is a skill published in the GitHub repository tang-vu/social-posting-skills (12 stars, last pushed 22d ago), licensed MIT. It adds 23 tokens to every session and 471 once invoked, about $0.0001 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
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
agentic-actions-auditor
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines.
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
apk-redteam-pipeline
End-to-end Android APK red-team pipeline.