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.
npx skills add TIKAZI/TIKAZ-AI-Skills --skill video-intelligencegit clone --depth 1 https://github.com/TIKAZI/TIKAZ-AI-SkillsWrote 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/tikazi/tikaz-ai-skills/video-intelligence)<a href="https://agentmods.dev/skills/tikazi/tikaz-ai-skills/video-intelligence"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/video-intelligence/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/tikazi/tikaz-ai-skills/video-intelligence"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/video-intelligence.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 | $0.00054 | $0.00542 |
| Opus 5 | $0.00027 | $0.00271 |
| Sonnet 5 | $0.00011 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
video-intelligence 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Intelligence
Designed, integrated, refactored, and continuously maintained by TIKAZ.
Inputs and routing
Accept one or more video URLs, stable platform IDs, podcast links, or local media files plus the question and desired evidence depth. Use video-platform-reader directly when reading and evidence cards are the whole outcome; use the orchestrator for multi-source synthesis and downstream handoffs.
TIKAZ method
- Create a source ledger before analysis: platform, stable ID, author, date, duration, access status, and evidence available.
- Route acquisition to
video-platform-reader; never treat a title, description, or search snippet as watched content. - Assign an evidence level:
L0 metadata,L1 native transcript,L2 timestamped ASR,L3 transcript + keyframes, orL4 media evidence + primary-source verification. - Separate five statement types: source claim, transcript evidence, visual observation, external verification, and TIKAZ inference/recommendation.
- Produce one card per source before cross-source synthesis.
- Merge only after recording agreements, conflicts, dependencies, missing evidence, and confidence.
Handoff contract
Pass structured source records, not prose-only summaries. Knowledge capture may begin only after every requested source has an access and evidence status.
Completion gate
Finish when every source is accounted for, important visual claims are checked or explicitly unverified, timestamps support key claims where available, and synthesized recommendations cite their evidence path.
Output, fallback, and limits
Return a source ledger, evidence cards, statement types, timestamps, visual checks, conflicts, confidence, inaccessible sources, and synthesis. If subtitles, ASR, keyframes, or official verification are unavailable, lower the evidence level and preserve the gap. Never bypass authentication, DRM, paywalls, or platform controls, and never describe metadata as watched content.
Validate that every requested source has an access status and every key conclusion has a visible evidence path or an explicit unverified label.
What ships with it
8 files 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.
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 · 44 lines · 54 tokens per session scan A bd6a0012d267
video-intelligence is a skill published in the GitHub repository TIKAZI/TIKAZ-AI-Skills (6 stars, last pushed 9d ago), licensed MIT. It adds 54 tokens to every session and 542 once invoked, about $0.0003 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
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
optimize-claude-opus-5-prompts
Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus 5 prompt…
optimize-claude-fable-5-prompts
A prompt-editing method for Claude Fable 5, an AI model. It turns rough or existing instructions into clearer prompts while keeping the original goal and important limits.
optimize-gpt-5-6-prompts
A guide for improving prompts written for OpenAI’s GPT-5.6 models, including GPT-5.6 Sol.