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 agentmods add agents/noelpuig/claude-explains/plannergit clone --depth 1 https://github.com/noelpuig/claude-explainsWrote 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/planner)<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>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 | $0.00029 | $0.02181 |
| Opus 5 | $0.00015 | $0.01091 |
| Sonnet 5 | $0.00006 | $0.00436 |
| Haiku 4.5 | $0.00003 | $0.00218 |
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.
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
- Read the CLI design guide:
node ../cli/bin/claude-video.js --help-design - Read the CLI format guide:
node ../cli/bin/claude-video.js --help-format - Read the CLI components guide:
node ../cli/bin/claude-video.js --help-components - 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. - If additional source material was provided outside references/, read it too
- Read
pipeline/briefings/planner.mdfor 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"
]
}
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.
- 3d ago First seen · 216 lines · 29 tokens per session scan A 4261e76ec863
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.
Other agents, from other repositories
genblaze-maintainer
The Genblaze Maintainer — autonomous guardian of the Genblaze repo. Resolves GitHub issues end-to-end (branch → TDD fix → verify → merge-ready PR) and audits functional integrity, security, code quality, documentation, AI agent standards, and dependency health. Invoke with an issue number to fix it, with no prompt to…
evolve-auditor
Single-pass review agent for the Evolve Loop. Covers code quality, security, pipeline integrity, and eval gating. READ-ONLY — flags MEDIUM+ issues.
evolve-builder
Implementation agent for the Evolve Loop. Designs, builds, and self-verifies changes in an isolated worktree with TDD and minimal-change principles.
agent-templates
Base schemas and context blocks for all agents.
evolve-builder-reference
Sections here are loaded only when specific build conditions activate. In the common build path, none of this is needed. v8.64.0 Campaign D Cycle D2 split.
evolve-intent
Pre-Scout intent capture agent. Takes a vague user goal, classifies it via the Ask-when-Needed framework, and emits a structured intent.md with goal/non-goals/constraints/interfaces/acceptance/assumptions/challenged-premises/risk-level. Mandatory ≥1 challenged premise.