Borrowing it
Nothing to install: this file belongs to bnayahu/journeycast. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bnayahu/journeycast/main/CLAUDE.mdgit clone --depth 1 https://github.com/bnayahu/journeycastWrote 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/instructions/bnayahu/journeycast/claude-md)<a href="https://agentmods.dev/instructions/bnayahu/journeycast/claude-md"><img src="https://agentmods.dev/badge/instructions/bnayahu/journeycast/claude-md.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 5.1 | $0.01161 | $0.01161 |
| Opus 5 | $0.00580 | $0.00580 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
journeycast CLAUDE.md 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 7d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Current state
Pre-implementation. The repo currently contains only the approved design spec at
docs/superpowers/specs/2026-07-14-journeycast-design.md. No engine/, skills/,
commands/, fixtures/, or .claude-plugin/ directories exist yet. When implementing,
read the spec first — it is the source of truth for layout, contracts, and decisions,
and the sections below summarize the parts that require reading multiple (future) files
to hold in your head at once.
What JourneyCast is
A Claude Code plugin that turns a pull request into a narrated demo video of the UI journey the PR introduces. The whole design hinges on one boundary:
- Claude (skill-guided, non-deterministic) does the reasoning: read the PR, explore
the app, author
journey.yaml, orchestrate the run. - The engine (plain Node/TS scripts, no LLM) does the mechanical media work: capture the real UI with Playwright, synthesize narration, render/compose with Remotion + ffmpeg.
The only things crossing that boundary are data artifacts: journey.yaml flows down
into the engine; capture results and the final MP4 flow back up. Keep that boundary intact —
never put LLM calls inside the engine, and never hand-code per-video rendering logic in a
skill. This separation is what makes re-renders and CI runnable with no Claude session.
journey.yaml — the contract
Single source of truth for both capture and render. Human-editable, validated with ajv
against skills/deriving-journeys/journey.schema.json. A run has an explicit human-edit
gate: Claude drafts the file, the human edits it, then capture + render proceed. The gate
is always an explicit stop, never a silent pass-through.
Scene kinds (the MVP scene library): title, screen, action, callout, outro.
Adding a new visual = adding a new scene kind in two places: a schema entry and a
matching Remotion component. This is the only extensibility mechanism — do not generate
per-video code.
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.
- 7d ago First seen · 83 lines · 1,161 tokens per session scan A 6ed49722c02a
journeycast CLAUDE.md is an instructions file published in the GitHub repository bnayahu/journeycast (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,161 tokens to every session, about $0.0058 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.