journeycast

journeycast is a command for Claude Code from bnayahu/journeycast. It costs 16 tokens per session (386 once invoked), scanned A, original, Apache-2.0.

A command that turns a pull request—a proposed code change—into a narrated video showing the user interface journey it adds or changes.

In plain words
What is it for?
It helps draft a journey description from a pull request, capture the described flow, render an MP4 video, and produce a subtitle file.
Why use it?
It separates drafting, human review, screen capture, and video rendering so the journey can be checked before the final video is made.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the journeycast plugin — 3 skills, 1 command shipped together

Good fit It helps draft a journey description from a pull request, capture the described flow, render an MP4 video, and produce a subtitle file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/bnayahu/journeycast/journeycast
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.

Clone the repo
git clone --depth 1 https://github.com/bnayahu/journeycast

Made for: Claude Code.

Or install journeycast, the plugin that ships this one along with the rest of its 3 skills, 1 command.

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 journeycast

README.md
[![agentmods](https://agentmods.dev/badge/commands/bnayahu/journeycast/journeycast/github.svg)](https://agentmods.dev/commands/bnayahu/journeycast/journeycast)
Your own site
<a href="https://agentmods.dev/commands/bnayahu/journeycast/journeycast"><img src="https://agentmods.dev/badge/commands/bnayahu/journeycast/journeycast/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 journeycast

Your own site · 80×15
<a href="https://agentmods.dev/commands/bnayahu/journeycast/journeycast"><img src="https://agentmods.dev/badge/commands/bnayahu/journeycast/journeycast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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 $0.00016 $0.00386
Opus 5 $0.00008 $0.00193
Sonnet 5 $0.00003 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 9d ago against content hash a9536fe033d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

journeycast 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 9d 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.

commands/journeycast.md · 25 lines

What it actually says

/journeycast

Arguments: $ARGUMENTS

Dispatch on the first argument:

  • draft <pr> — Use the deriving-journeys skill to draft journey.yaml from PR <pr>. End at the human-edit gate: present the file and stop. Do not capture or render.

  • capture — Use the capturing-journeys skill on the current journey.yaml.

  • render — Use the rendering-videos skill to produce the MP4.

  • run <pr> — Full flow: draft <pr>pause for human review/edit of journey.yaml → wait for the user to say to continue → capturerender. The pause is a real stop; never proceed through it automatically.

If no subcommand is given, briefly explain these four subcommands and ask which to run.

Output location. Artifacts go in the target repository (the repo the PR belongs to), not the journeycast clone. Default: docs/journeycast/pr-<pr>/ (bare PR number) holds the committed journey.yaml, <feature>.mp4, and <feature>.srt. Capture/render scratch stays under out/pr-<pr>/ in the journeycast clone (gitignored). See the deriving-journeys Output location section for the full convention.

The engine (engine/capture.mjs, engine/render.mjs, engine/validate.mjs) does all mechanical media work and is runnable without a Claude session; the skills only orchestrate it.

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. 9d ago First seen · 25 lines · 16 tokens per session scan A a9536fe033d2

Subscribe to this mod's changes

journeycast is a command published in the GitHub repository bnayahu/journeycast (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 386 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.