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 mediagit 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)<a href="https://agentmods.dev/skills/minara-ai/media-agent/media"><img src="https://agentmods.dev/badge/skills/minara-ai/media-agent/media/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"><img src="https://agentmods.dev/badge/skills/minara-ai/media-agent/media.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 | $0.00064 | $0.01035 |
| Opus 5 | $0.00032 | $0.00517 |
| Sonnet 5 | $0.00013 | $0.00207 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
media scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/media — Full Content Creation Workflow
The complete guided workflow: idea → write → image → publish.
This orchestrator is a thin sequencer. For each stage, it reads the shared library files and follows the same logic as the individual sub-skills.
Prerequisites
Read these shared library files before proceeding:
- Read
lib/adapter-discovery.md - Read
lib/manifest-ops.md - Read
lib/image-processing.md
Step 0: Detect State & Resume
Check if there's an in-progress post:
# Find posts with draft variants (not yet fully published)
for dir in content/posts/*/; do
if [ -f "$dir/manifest.yaml" ]; then
has_draft=$(python3 -c "
import yaml
with open('${dir}manifest.yaml') as f:
m = yaml.safe_load(f)
variants = m.get('variants', {})
drafts = [k for k,v in variants.items() if v.get('status') in ('draft','pending','failed')]
print('yes' if drafts else 'no')
" 2>/dev/null)
if [ "$has_draft" = "yes" ]; then
echo "IN_PROGRESS: $dir"
fi
fi
done
If an in-progress post is found, use AskUserQuestion: "Found an in-progress post: ''. What would you like to do?"
- A) Resume this post (continue from where we left off)
- B) Start a new post
- C) Finish publishing this post (jump to /media-publish)
Detecting resume stage
Read the manifest to determine which stage to resume from:
- No
source.md→ resume from ideation/writing (Stage 1-2) source.mdexists but no variants → resume from variant generation (Stage 2, Step 5)- Variants exist but no assets → resume from image generation (Stage 3)
- Assets exist but variants are
draft→ resume from publishing (Stage 4)
Stage 1: Ideation
Read skills/media-idea/SKILL.md and follow its workflow.
This stage produces a brief.yaml in the post directory.
If a brief.yaml already exists (resume scenario), skip to Stage 2.
Stage 2: Writing
Read skills/media-write/SKILL.md and follow its workflow.
This stage produces:
source.md(canonical content)variants/<name>.mdfor each platformmanifest.yaml
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 · 148 lines · 64 tokens per session scan A bc205c6ca1ec
media is a skill published in the GitHub repository Minara-AI/media-agent (6 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 1,035 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-cover
A novel-cover generator that creates a cover with the book title and author name. It chooses a visual style from the book information and can use Codex's image-generation tool.
sepia-hemingway
Use when a user asks to write or revise fiction in the Hemingway manner, or asks for strong de-AI on a story; applies Sepia's built-in Hemingway voice profile.
guofeng-threejs
A skill for creating Chinese-style real-time 3D web visuals with Three.js, a JavaScript library for displaying 3D graphics in a browser. It focuses on ink-wash, blue-green landscape, mural, paper-cut, and other non-realistic styles.
guochao-visual-cn
A prompt-writing guide for generating Chinese-inspired illustrations and other visual designs. It distinguishes twelve Chinese artistic styles, such as ink painting, gongbi painting, blue-green landscapes, and Dunhuang murals.
diagram
Generate modern reviewable diagrams (system architecture, workflow, data flow, sequence, ER, state-machine, C4) via OpenRouter image-gen or LLM-emitted SVG. Auto-classifies diagram type from prompt; --type to override. Default scratch output goes to the resolved workbench visuals path; --versioned writes git-trackable…