Borrowing it
Nothing to install: this file belongs to norton77930/corpus-ingest-core. 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/norton77930/corpus-ingest-core/main/.agents/skills/x-video-ingest/SKILL.mdgit clone --depth 1 https://github.com/norton77930/corpus-ingest-coreWrote 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/skills/norton77930/corpus-ingest-core/x-video-ingest)<a href="https://agentmods.dev/skills/norton77930/corpus-ingest-core/x-video-ingest"><img src="https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/x-video-ingest/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.
<a href="https://agentmods.dev/skills/norton77930/corpus-ingest-core/x-video-ingest"><img src="https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/x-video-ingest.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00388 |
| Opus 5 | $0.00012 | $0.00194 |
| Sonnet 5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
x-video-ingest 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 11d 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.
What it actually says
X Video Ingest
Use the mounted MCP tool to bring the video from one X post into the corpus. Keep the human in control: one preview, one explicit approval, one matching confirmed call, then stop.
Procedure
- Call
ingest_x_videowith the exacturlthe user gave andconfirm=false. - Explain the derived podcast id and episode reference, the resolved title, the planned writes, and the returned warnings.
- State plainly that this preview already resolved public source metadata over the network. It is zero-write but not zero-network, so the source host has already been contacted once before the human is asked anything.
- Explain what confirming would add: downloading the source media, extracting audio, transcribing locally on this machine, and writing corpus artifacts. The source video itself is never kept.
- Ask one explicit approval question and wait for the answer.
- Treat absent, ambiguous, conditional, or negative replies as no approval.
- After explicit approval, call the same MCP tool with the same
urlandconfirm=true, exactly once. - Pass
titleonly when the human supplied one, andforce=trueonly when the human explicitly asked to overwrite existing artifacts. This tool needs noapi_cost_ackbecause it calls no external LLM. - Report the bounded result and stop. Do not start another preview or action unless the user makes a new request.
The confirmed run does not rebuild the search index. Report the cache-stale warning and let the human decide when to rebuild.
If the MCP tool is unavailable, report a setup problem. Do not use a terminal, CLI, another side-effect tool, cron/scheduler, retry, or autonomous loop as a fallback.
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.
- 11d ago First seen · 27 lines · 23 tokens per session scan A 24faf9a3efdb
x-video-ingest is a skill published in the GitHub repository norton77930/corpus-ingest-core (2 stars, last pushed 11d ago), licensed MIT. It adds 23 tokens to every session and 388 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 skills, from other repositories
openkb-deck-neon
A skill for creating a single-file HTML slide deck from content stored in OpenKB, a knowledge-base chat system. It defines a dark, high-tech visual style using neon colors, glow effects, and glass-like panels.
openkb-deck-editorial
A tool for creating a single-file HTML slide presentation from compiled knowledge-base content. Its visual style uses a warm cream background, serif typography, and brick-red accents.
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.