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 Minara-AI/media-agent --skill media-imagegit clone --depth 1 https://github.com/Minara-AI/media-agentWrote 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/minara-ai/media-agent/media-image)<a href="https://agentmods.dev/skills/minara-ai/media-agent/media-image"><img src="https://agentmods.dev/badge/skills/minara-ai/media-agent/media-image/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/minara-ai/media-agent/media-image"><img src="https://agentmods.dev/badge/skills/minara-ai/media-agent/media-image.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 | $0.00058 | $0.01575 |
| Opus 5.5 | $0.00023 | $0.00630 |
| Sonnet 5.5 | $0.00012 | $0.00315 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
media-image scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
URL=$(curl -s https://api.openai.com/v1/images/generations \ How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/media-image — Image Generation & Management
Generate contextual images for your post and resize them for each platform.
Uses excalidraw-skill for diagrams and illustrations (hand-drawn Excalidraw style). Optionally uses DALL-E for photo-style hero images.
Prerequisites
Before starting, read these shared library files:
- Read
lib/image-processing.mdfor resizing commands and platform sizes - Read
lib/manifest-ops.mdfor updating the manifest - Read
lib/adapter-discovery.mdfor platform image size requirements
Step 1: Locate the Post
If the user specifies a post path, use it. Otherwise, find the most recent post:
ls -dt content/posts/*/ 2>/dev/null | head -1
Read source.md to understand the content. Read manifest.yaml for existing state.
Step 2: Check Dependencies
echo "=== Image Dependencies ==="
# Check ImageMagick (for resizing)
which convert >/dev/null 2>&1 && echo "[OK] ImageMagick" || echo "[MISSING] ImageMagick — needed for resizing (brew install imagemagick)"
# Check excalidraw-skill (for diagrams)
EXCALIDRAW_SKILL=""
[ -f ".claude/skills/excalidraw-skill/skill/SKILL.md" ] && EXCALIDRAW_SKILL="local"
[ -f "$HOME/.claude/skills/excalidraw-skill/skill/SKILL.md" ] && EXCALIDRAW_SKILL="global"
[ -n "$EXCALIDRAW_SKILL" ] && echo "[OK] excalidraw-skill ($EXCALIDRAW_SKILL)" || echo "[MISSING] excalidraw-skill — install from https://github.com/Minara-AI/excalidraw-skill"
# Check OpenAI API key (optional, for photo-style hero images)
grep -q "^OPENAI_API_KEY=." .env 2>/dev/null && echo "[OK] DALL-E (photo hero images)" || echo "[OPTIONAL] No OPENAI_API_KEY — DALL-E unavailable, using excalidraw only"
Step 3: Plan Images
Analyze source.md and identify where images would add value:
- Hero/cover image: A cover image that captures the article's theme
- In-article diagrams: Architecture diagrams, flowcharts, concept maps
- In-article illustrations: Visual explanations for complex concepts
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.
- 2mo ago First seen · 182 lines · 58 tokens per session scan A 1751268469a8
media-image is a skill published in the GitHub repository Minara-AI/media-agent (7 stars, last pushed 7mo ago), licensed MIT. It adds 58 tokens to every session and 1,575 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
media-image compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| media-imageMinara-AI/media-agent | Skill | 7 | 7mo ago | MIT | A | 58 | Claude Code |
| story-reviewzenstory-ai/oh-story-claudecode | Skill | 8.6k | today | MIT | A | 74 | Claude Code |
| story-setupzenstory-ai/oh-story-claudecode | Skill | 8.6k | today | MIT | A | 97 | Claude Code |
| storyzenstory-ai/oh-story-claudecode | Skill | 8.6k | today | MIT | A | 63 | Claude Code |
| story-deslopzenstory-ai/oh-story-claudecode | Skill | 8.6k | today | MIT | A | 70 | Claude Code |
| story-importzenstory-ai/oh-story-claudecode | Skill | 8.6k | today | MIT | A | 98 | Claude Code |
| story-short-analyzezenstory-ai/oh-story-claudecode | Skill | 8.6k | today | MIT | A | 226 | Claude Code |