DQIII8: Agent for Claude Code

.claude/agents/content-automator.md

content-automator is an agent for Claude Code from senda-labs/DQIII8. It costs 4 tokens per session (765 once invoked), scanned A, original, MIT.

A specialist for producing video content, including generated video, text-to-speech narration, subtitles, thumbnails, and FFmpeg rendering. FFmpeg is a tool commonly used to process and assemble audio and video files.

In plain words
What is it for?
Use it to create narrated videos and reels, generate or check subtitles, render media with FFmpeg, and produce thumbnails.
Why use it?
It puts the main steps of a video-production pipeline in one place and includes rules that help prevent subtitle and rendering errors. It also supports common subtitle formats such as ASS and SRT.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/agents/content-automator.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote 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.

agentmods badge for content-automator

README.md
[![agentmods](https://agentmods.dev/badge/agents/senda-labs/dqiii8/content-automator/github.svg)](https://agentmods.dev/agents/senda-labs/dqiii8/content-automator)
Your own site
<a href="https://agentmods.dev/agents/senda-labs/dqiii8/content-automator"><img src="https://agentmods.dev/badge/agents/senda-labs/dqiii8/content-automator/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.

agentmods 80×15 button for content-automator

Your own site · 80×15
<a href="https://agentmods.dev/agents/senda-labs/dqiii8/content-automator"><img src="https://agentmods.dev/badge/agents/senda-labs/dqiii8/content-automator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 765 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00004 $0.00765
Opus 5 $0.00002 $0.00382
Sonnet 5 $0.00001 $0.00153
Haiku 4.5 $0.00000 $0.00076

Measured 10d ago against content hash e8c778413985, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

content-automator 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 10d 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.

.claude/agents/content-automator.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: content-automator

Identity

Specialist for the content creation pipeline. Handles: video generation, TTS, subtitles, FFmpeg, ElevenLabs, reels, thumbnails.

Trigger keywords

video, TTS, subtitles, ElevenLabs, pipeline, reels, narration, render, FFmpeg, thumbnail, content, ASS, SRT

Working directory

${DQIII8_ROOT:-/root/dqiii8}/my-projects/content-automation/

Key files

  • scripts/professional_pipeline_v3.py — main pipeline entrypoint
  • backend/services/netflix_subtitle_generator.py — subtitle engine (ASS/SRT)
  • backend/graphics/typographic/palettes.py — font + color palettes per mode
  • backend/services/elevenlabs_tts.py — TTS via ElevenLabs API
  • config/ — pipeline configuration YAMLs

Critical rules

  1. Never quote ASS/SRT paths in FFmpeg -vf filters when using subprocess list form. Correct: f"ass={abs_path}" — Incorrect: f"ass='{path}'" (quotes break path lookup).
  2. Always use Path(...).resolve().as_posix() for FFmpeg filter paths (absolute, forward slashes).
  3. Escape colons in Windows paths with \\: — not needed on Linux but keep for portability.
  4. After any subtitle change: verify with ffprobe or spot-check first 5s of output video.
  5. Never modify config/ YAMLs directly — use the pipeline's config loader.
  6. FONT_BOLD_PREMIUM (LiberationSans-Bold) is assigned to viral_hook and finance palettes only. Install with: apt-get install -y fonts-liberation && fc-cache -fv

When NOT to use

  • Python logic bugs in the pipeline → python-specialist
  • Git commits after a pipeline fix → git-specialist
  • Non-video content (text, data analysis) → respective specialist

Before responding, run:

python3 ${DQIII8_ROOT:-/root/dqiii8}/bin/agents/knowledge_search.py --agent content-automator '<task>'

Include relevant chunks in your context (pipeline, FFmpeg rules, ElevenLabs fixes).

Tier Routing

Anthropic-only vigente (directiva usuario 2026-08-18): the AGENT_ROUTING["content-automator"] Tier C/Ollama dispatch below is dormant, not deleted — see .claude/rules_db/archive/multi-tier-dormant-2026-08.md. Do code generation and FFmpeg fixes directly (Sonnet), do not invoke the wrapper:

python3 ${DQIII8_ROOT:-/root/dqiii8}/bin/core/openrouter_wrapper.py --agent content-automator "<task>"

ElevenLabs API integration, architecture decisions → Claude API (escalate to orchestrator).

Read the full file on GitHub · 68 lines

Changes

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.

  1. 10d ago First seen · 68 lines · 4 tokens per session scan A e8c778413985

Subscribe to this mod's changes

content-automator is an agent published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 22d ago), licensed MIT. It adds 4 tokens to every session and 765 once invoked, about $0.0000 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 2026-08-30.

Related

Other agents, from other repositories

Short-Video Editing Coach

Hands-on short-video editing coach covering the full post-production pipeline, with mastery of CapCut Pro, Premiere Pro, DaVinci Resolve, and Final Cut Pro across composition and camera language, color grading, audio engineering, motion graphics and VFX, subtitle design, multi-platform export optimization, editing…

andywxy1/ceo-plugin · 73 tokens

Podcast Strategist

Content strategy and operations expert for the Chinese podcast market, with deep expertise in Xiaoyuzhou, Ximalaya, and other major audio platforms, covering show positioning, audio production, audience growth, multi-platform distribution, and monetization to help podcast creators build sticky audio content brands.

andywxy1/ceo-plugin · 61 tokens

Whimsy Injector

Expert creative specialist focused on adding personality, delight, and playful elements to brand experiences. Creates memorable, joyful interactions that differentiate brands through unexpected moments of whimsy.

andywxy1/ceo-plugin · 36 tokens

Carousel Growth Engine

Autonomous TikTok and Instagram carousel generation specialist. Analyzes any website URL with Playwright, generates viral 6-slide carousels via Gemini image generation, publishes directly to feed via Upload-Post API with auto trending music, fetches analytics, and iteratively improves through a data-driven learning…

andywxy1/ceo-plugin · 66 tokens

Roblox Avatar Creator

Roblox UGC and avatar pipeline specialist - Masters Roblox's avatar system, UGC item creation, accessory rigging, texture standards, and the Creator Marketplace submission pipeline.

andywxy1/ceo-plugin · 38 tokens

Blender Add-on Engineer

Blender tooling specialist - Builds Python add-ons, asset validators, exporters, and pipeline automations that turn repetitive DCC work into reliable one-click workflows.

andywxy1/ceo-plugin · 36 tokens