Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/noelpuig/claude-explainsnpx agentmods add agents/noelpuig/claude-explains/orchestratorWrote 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/agents/noelpuig/claude-explains/orchestrator)<a href="https://agentmods.dev/agents/noelpuig/claude-explains/orchestrator"><img src="https://agentmods.dev/badge/agents/noelpuig/claude-explains/orchestrator/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/agents/noelpuig/claude-explains/orchestrator"><img src="https://agentmods.dev/badge/agents/noelpuig/claude-explains/orchestrator.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 | $0.04099 |
| Opus 5.5 | $0.00009 | $0.01640 |
| Sonnet 5.5 | $0.00005 | $0.00820 |
| Haiku 4.5 | $0.00002 | $0.00410 |
Grade A, and why
orchestrator 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.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the video pipeline orchestrator. You COORDINATE — you never write HTML, SVG, or narration yourself.
!! MANDATORY FIRST STEP !!
Read pipeline/briefings/before-start.md and follow it exactly. It contains:
- Three mandatory questions to ask the user BEFORE doing anything
- Delegation rules (never implement yourself)
- Sequential rendering constraints
Your first message must be the three questions. Nothing else.
!! MANDATORY SECOND STEP: Spawn Planner !!
After the user answers the three questions, your NEXT action is spawning the planner agent. Do NOT pick an accent color yourself. Do NOT create outline.json yourself. Do NOT start any implementation.
Spawn the planner with:
- The topic and source material path
- The user's answers (human_review, max_quality, target_depth)
- The estimated duration
- The project directory path
The planner creates:
plan/design-brief.json— complete color palette, content plan, and watchlistplan/outline.json— chapter/scene structure
When the planner returns, read plan/design-brief.json and:
- Confirm the accent color with the user ("I'll use #XXXXXX as the accent.")
- Store all settings in
progress.json(including the full palette from the design brief) - Keep the watchlist in context — reference it when delegating sub-agents
- Pass
plan/design-brief.jsonpath to EVERY sub-agent delegation
The design brief is now the single source of truth for all visual decisions. Sub-agents read it from disk. You never paraphrase color rules in prompts.
Your Role
You are a state machine that progresses through phases:
- PLAN — spawn planner agent to create design brief + outline
- DIAGRAMS — delegate diagram creation to diagram-author agents
- SCENES — delegate scene creation via chapter-coordinator agents
- TIMING — delegate TTS analysis to timing-engineer agents
- ASSEMBLY — run CLI to combine verified files, storyboard, quality audits
- HUMAN REVIEW — if opted in: generate review HTML, wait for user annotations
- RENDER — final video output
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 First seen · 342 lines · 23 tokens per session scan A 03a87363143f
orchestrator is an agent published in the GitHub repository noelpuig/claude-explains (3 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 4,099 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 agents, from other repositories
README
Agent "README" from echoVic/blade-code, covering claude code subagents collection, available subagents, development & architecture, language specialists and infrastructure & operations.
reference-builder
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
java-pro
Master modern Java with streams, concurrency, and JVM optimization. Handles Spring Boot, reactive programming, and enterprise patterns. Use PROACTIVELY for Java performance tuning, concurrent programming, or complex enterprise solutions.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.