A workflow for processing a Notion inbox of video links. It downloads and transcribes videos, classifies the notes by project, and writes the results to Notion and matching local files.

Use it to fetch new inbox items, create transcripts, assign titles and projects, summarize them, record their platform, and route the results to the approved destinations.

It turns a queue of unprocessed video links into organized, searchable notes without requiring manual transcription and filing.

notes-inbox — Skill for Claude Code and Codex by roarista

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 roarista/awesome-harness --skill notes-inbox

Clone the repo

git clone --depth 1 https://github.com/roarista/awesome-harness

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/roarista/awesome-harness/notes-inbox/github.svg)](https://agentmods.dev/skills/roarista/awesome-harness/notes-inbox)

Your own site

<a href="https://agentmods.dev/skills/roarista/awesome-harness/notes-inbox"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/notes-inbox/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/roarista/awesome-harness/notes-inbox"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/notes-inbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 694 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.

Model	Per session	Once invoked
Fable 5.1	$0.00078	$0.00694
Opus 5	$0.00039	$0.00347
Sonnet 5	$0.00016	$0.00139
Haiku 4.5	$0.00008	$0.00069

Measured 9d ago against content hash 6372079ed616, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

notes-inbox 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.

skills/notes-inbox/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

notes-inbox — procesar el Video Inbox

Pipeline en ~/NotesPipeline/ (lee su CLAUDE.md). Config e IDs en ~/NotesPipeline/.env. Cero API credits de Claude: la transcripción es yt-dlp + ElevenLabs; la clasificación la haces TÚ en esta sesión (suscripción).

Pasos

Fetch + transcribe: cd ~/NotesPipeline && ./run.sh
- Consulta filas Status=New del Inbox via REST (scripts/notion_io.py list-new), transcribe EN SERIE con scripts/ingest.py, deja queue/<page_id>.json, marca Transcribed.
- Si notion_io.py check falla con 404: la página 🧠 Second Brain no está compartida con la integración "connection" — pedir a Ro el clic (••• → Connections) o, como fallback, leer el inbox via Notion MCP y correr ingest.py a mano por URL.
Clasifica cada queue/*.json que no tenga .routed marker: lee transcript y decide {title (corto, descriptivo), project, summary (3 bullets), platform}. Proyectos válidos: intrn, video-pipeline, vividlist, foreclosure-homes, ui, bible-pipeline, open-source, resume-linkedin, claude-code-tips, ideas, other.
Escribe doble:
- Notion: python3 scripts/notion_io.py write-result --page-id <id> --json <resultfile> (actualiza fila → Routed + crea subpágina Transcript). Si REST no disponible, usar MCP.
- Local: ~/Notes/<project>/new/<YYYY-MM-DD>-<slug>.md con frontmatter: notion_page_id, source_url, platform, status: new, summary, y el transcript como body.
Marca el queue file procesado: crea queue/<page_id>.routed (vacío).
Sync de vuelta: python3 scripts/sync_status.py (refleja moves locales integrated/discarded → Status en Notion).
Reporta a Ro: cuántos videos, títulos y a qué proyecto fue cada uno.

Reglas

CPU bajo: serie, nunca paralelo; nunca whisper local.
No borrar queue files (son el caché de idempotencia).
Si un video falla (link muerto, video privado), marca la fila Status=Discarded con Summary explicando, y sigue.

Read the full file on GitHub · 41 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.

9d ago First seen · 41 lines · 78 tokens per session scan A 6372079ed616

Subscribe to this mod's changes

notes-inbox is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 13d ago), licensed MIT. It adds 78 tokens to every session and 694 once invoked, about $0.0004 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.

Productivity Research

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

notes-inbox