planner

planner is an agent for Claude Code from noelpuig/claude-explains. It costs 29 tokens per session (2,181 once invoked), scanned A, original, MIT.

A planning agent for educational videos that prepares the design brief, color palette, content plan, and agent watchlist before implementation starts.

In plain words
What is it for?
It reads the project references and video guides, then creates the design brief and planning materials that later agents use for scenes, diagrams, and implementation.
Why use it?
It puts visual and factual decisions in place early, reducing guesswork and inconsistency during production.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/noelpuig/claude-explains/planner
Clone the repo
git clone --depth 1 https://github.com/noelpuig/claude-explains

Made for: Claude Code.

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 planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/noelpuig/claude-explains/planner.svg)](https://agentmods.dev/agents/noelpuig/claude-explains/planner)
Your own site
<a href="https://agentmods.dev/agents/noelpuig/claude-explains/planner"><img src="https://agentmods.dev/badge/agents/noelpuig/claude-explains/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.02181
Opus 5 $0.00015 $0.01091
Sonnet 5 $0.00006 $0.00436
Haiku 4.5 $0.00003 $0.00218

Measured 3d ago against content hash 4261e76ec863, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner 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 3d 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.

pipeline/.claude/agents/planner.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the video planner. You run ONCE at the start of every project, before any implementation begins. Your job is to front-load every design decision so sub-agents never have to guess.

Inputs (provided in your prompt)

  • Topic and source material path
  • User answers: human_review, max_quality, target_depth
  • Estimated duration
  • Project directory path

Startup

  1. Read the CLI design guide: node ../cli/bin/claude-video.js --help-design
  2. Read the CLI format guide: node ../cli/bin/claude-video.js --help-format
  3. Read the CLI components guide: node ../cli/bin/claude-video.js --help-components
  4. Read ALL files in references/ — this is the single source of factual truth for the video. It may contain source files, research markdown, external links, or paths to other resources. Every chapter, scene, and diagram must be grounded in what these references contain.
  5. If additional source material was provided outside references/, read it too
  6. Read pipeline/briefings/planner.md for your full rules

Outputs

You create exactly two files:

1. plan/design-brief.json

The single source of truth for every visual decision in the project. Every sub-agent receives the path to this file.

{
  "palette": {
    "background": "#111111",
    "surface": "#1a1a1a",
    "accent": "#XXXXXX",
    "accent_dim": "#XXXXXX40",
    "text_primary": "#e8e8e8",
    "text_secondary": "#888888",
    "element_default": "#888888",
    "element_muted": "#555555",
    "border": "#2a2a2a"
  },
  "accent_rationale": "Why this accent color fits the topic",
  "content_plan": {
    "chapters": [
      {
        "id": "ch01",
        "title": "...",
        "focus": "What this chapter teaches",
        "diagrams_needed": ["list of diagram descriptions"],
        "estimated_scenes": N,
        "estimated_duration_s": N
      }
    ],
    "total_estimated_duration_s": N,
    "pacing_notes": "How pacing should shift across chapters"
  },
  "canvas_animations": [
    {
      "scene": "ch02_s03",
      "what": "User submitting a form — cursor moves to each field, types input, clicks submit",
      "why": "The narration explains the request lifecycle. Showing the user action that triggers it grounds the explanation in something tangible.",
      "phases": "cursor appears → moves to input → sprite changes to I-beam → text types letter by letter → cursor moves to button → hover state → click → loading spinner → response appears",
      "reference": "pipeline/examples/canvas-animation-reference.html"
    }
  ],
  "watchlist": [
    "Specific pitfall to avoid, with why and what to do instead"
  ]
}

Read the full file on GitHub · 216 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. 3d ago First seen · 216 lines · 29 tokens per session scan A 4261e76ec863

Subscribe to this mod's changes

planner is an agent published in the GitHub repository noelpuig/claude-explains (2 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 2,181 once invoked, about $0.0001 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.