broll-onboarding

broll-onboarding is a skill for Codex from erduo1998-cell/erduo-broll-loop-engineering. It costs 28 tokens per session (959 once invoked), scanned A, original, MIT.

An environment-readiness checker for a B-roll video production setup. It checks whether the machine and required tools are ready, and coordinates approved repairs when recorded readiness information is missing or outdated.

In plain words
What is it for?
Use it after installation or migration, after relevant tool or machine changes, when a requested backend is not marked ready, or when a production command fails because of the environment.
Why use it?
It prevents unnecessary setup work when the environment is already known to be ready, while flagging genuine changes or machine-related failures. It also keeps production tasks separate from environment diagnosis.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it after installation or migration, after relevant tool or machine changes, when a requested backend is not marked ready, or when a production command fails because of the environment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding
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.

Any agent
npx skills add erduo1998-cell/erduo-broll-loop-engineering --skill broll-onboarding
Clone the repo
git clone --depth 1 https://github.com/erduo1998-cell/erduo-broll-loop-engineering

Made for: Codex.

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 broll-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding/github.svg)](https://agentmods.dev/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding)
Your own site
<a href="https://agentmods.dev/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding"><img src="https://agentmods.dev/badge/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding/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 broll-onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding"><img src="https://agentmods.dev/badge/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 959 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00028 $0.00959
Opus 5 $0.00014 $0.00479
Sonnet 5 $0.00006 $0.00192
Haiku 4.5 $0.00003 $0.00096

Measured 9d ago against content hash d0fcdac40182, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

broll-onboarding 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.

erduo-broll-loop-engineering/stages/broll-onboarding/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

B-roll onboarding

Act only as the environment diagnostic and authorized repair coordinator. This is an exception path, not a stage in every production. Do not direct, collect media, write animation source, integrate, render, export, or judge aesthetics.

Dispatch gate

Accept only a compact JSON result from scripts/production-preflight.mjs with next: run-onboarding-diagnostic. If next is continue, do not run. If it is fix-production-input, return the input/output issue to Parent without doing environment inspection. fix-project-runtime also stays out of Onboarding and belongs to the bounded project-local Remotion bootstrap/repair path.

Valid diagnostic causes are limited to:

  • no readiness cache after installation or migration;
  • cached release, machine, architecture, Node major, installed Skill set, pinned HyperFrames version, or pinned official-Skills commit changed;
  • a requested backend is not recorded ready;
  • a production command actually failed and points to a machine/tool problem.

A new production run, SRT, project/output path, runtime-plan identity, command PATH, free-space value, or Pexels status is not a deep-cache invalidator.

Inputs

  • release and Skill roots;
  • preflight JSON and failed fact IDs;
  • mode: inspect or repair;
  • exact required backend set, if already planned;
  • in repair mode only, explicit authorization and the approved repair list;
  • previous readiness cache, when present.

Read ../../references/first-run-onboarding.md. Read runtime selection and capability references only when a failed backend fact requires them. Do not read film, craft, material, review, or rendering references.

Inspect once

Inspection is read-only. Check only the failed or stale installation facts and their direct prerequisites. Do not rescan production paths, parse the SRT, estimate its delivery size, inspect Pexels, or run both backends when only one failed.

Common installation facts are Node 22.20+, executable FFmpeg/FFprobe, release Skill discovery, release identity, and host/architecture. For HyperFrames, load the pinned official hyperframes and hyperframes-cli Skills, then run the release doctor and inspect its JSON. For Remotion, use only exact project-local remotion and @remotion/cli dependencies and direct local CLI evidence; never use global CLI or an npx download as proof.

Read the full file on GitHub · 106 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 106 lines · 28 tokens per session scan A d0fcdac40182

Subscribe to this mod's changes

broll-onboarding is a skill published in the GitHub repository erduo1998-cell/erduo-broll-loop-engineering (170 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 959 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 2026-08-30.