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 mateohysa/reelsfarm-mcp --skill reelsfarm-ai-avatarsgit clone --depth 1 https://github.com/mateohysa/reelsfarm-mcpWrote 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/mateohysa/reelsfarm-mcp/reelsfarm-ai-avatars)<a href="https://agentmods.dev/skills/mateohysa/reelsfarm-mcp/reelsfarm-ai-avatars"><img src="https://agentmods.dev/badge/skills/mateohysa/reelsfarm-mcp/reelsfarm-ai-avatars/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/mateohysa/reelsfarm-mcp/reelsfarm-ai-avatars"><img src="https://agentmods.dev/badge/skills/mateohysa/reelsfarm-mcp/reelsfarm-ai-avatars.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 | $0.00055 | $0.01261 |
| Opus 5.5 | $0.00022 | $0.00504 |
| Sonnet 5.5 | $0.00011 | $0.00252 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
reelsfarm-ai-avatars 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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ReelsFarm AI avatars
Generate AI images of people for marketing creatives with ReelsFarm, such as a creator-style selfie for a slideshow or a starting frame for a video. Edit a result in follow-up turns until it is right.
Setup
- Install the CLI:
npm install -g @reelsfarm/mcp-client. It provides thereelsfarmcommand. - Create an MCP API key in the MCP tab of the ReelsFarm account and set it as
REELSFARM_API_KEY. The key is shown only once. - Check the connection:
reelsfarm agent statusandreelsfarm account status --agent.
ReelsFarm is a paid service (https://reelsfarm.com). Creating media spends credits from the user's plan or trial. Without one, commands that create or publish return a link to choose a plan. Credential, connection-mode, and permanent-delete settings stay in the ReelsFarm dashboard and are not in the CLI.
Running actions
- Always add
--agent. It prints one JSON object withok,dataorerror, and anextStephint. - Preview first with
--dry-run. Nothing runs on the server. Tell the user what will be made and what it costs;reelsfarm account pricing --agentlists credit prices. - After the user approves, run the same command with
--yes --wait.--yesconfirms only the action the server prepared. It never changes the account's connection mode.--waitwaits for the job to finish. - If a response has
requiresConfirmation: true, ask the user, then run itsnextStep(reelsfarm confirm <id> --tool <tool> --agent). If that returns an operation id, follow it withreelsfarm operations wait --id <operationId> --agent. - Give each action one
--idempotency-keyand reuse it only to retry that same action after a timeout. Never start a second copy while the first may still be running.
Results
Say an image, video, or slideshow exists only when the response shows executionState: "COMPLETED", assetCreated: true, and a ReelsFarm asset id and URL. PREPARED or NOT_STARTED means nothing ran. ENQUEUED or PROCESSING means it is not finished. When the user asked for ReelsFarm, don't swap in another image or video generator.
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.
- 6d ago First seen · 87 lines · 55 tokens per session scan A b0f2ca06d71c
reelsfarm-ai-avatars is a skill published in the GitHub repository mateohysa/reelsfarm-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 1,261 once invoked, about $0.0002 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 2026-10-31.
reelsfarm-ai-avatars compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reelsfarm-ai-avatarsmateohysa/reelsfarm-mcp | Skill | 0 | 6d ago | MIT | A | 55 | Claude Code, Codex |
| narrator-ai-cliNarratorAI-Studio/narrator-ai-cli | Skill | 149 | 3mo ago | MIT | A | 73 | Claude Code |
| video-podcast-makerAgents365-ai/video-podcast-maker | Skill | 1.7k | 1mo ago | MIT | A | 214 | Claude Code |
| video-podcast-maker-liteAgents365-ai/video-podcast-maker | Skill | 1.7k | 1mo ago | MIT | A | 96 | Claude Code |
| video-podcast-maker-nanoAgents365-ai/video-podcast-maker | Skill | 1.7k | 1mo ago | MIT | A | 163 | Claude Code |
| frontend-designOrkas-AI/Orkas-VideoStudio | Skill | 344 | 2d ago | MIT | A | 57 | Claude Code, Codex |
| stage-planOrkas-AI/Orkas-VideoStudio | Skill | 344 | 2d ago | MIT | A | 0 | Claude Code, Codex |