Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/yt-pulseWrote 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/mishahanin/heading-os/yt-pulse)<a href="https://agentmods.dev/skills/mishahanin/heading-os/yt-pulse"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/yt-pulse/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/mishahanin/heading-os/yt-pulse"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/yt-pulse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 22 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00145 | $0.03328 |
| Opus 5 | $0.00072 | $0.01664 |
| Sonnet 5 | $0.00029 | $0.00666 |
| Haiku 4.5 | $0.00015 | $0.00333 |
Grade A, and why
yt-pulse scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
python -c "import urllib.request, json; r = urllib.request.urlopen('https://api.ipify.org?format=json', timeout=5); print(json.loads(r.read().decode())['ip'])" How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YT Pulse - YouTube Intelligence Scanner
Scan YouTube for trending content in any domain and identify what creators are talking about. Find the best video worth watching, and deliver an intelligence brief with 31C business relevance.
Variables
query: [required] Domain or topic to scan (e.g., "AI agents", "deep packet inspection", "sailing navigation", "cybersecurity threats 2026")
timeframe: [optional] 24h | 72h (default) | 7d | 30d
depth: [optional] quick (search + clustering only) | full (default, includes transcript analysis)
Instructions
Before executing, read:
context/strategy.md- Strategic priorities for relevance assessmentcontext/business-info.md- ODUN.ONE capabilitiescontext/pipeline.md- Active deals for relevance scoring
Configuration
Per-channel cap, browser cookie sourcing (default: Brave ClaudeCode profile via yt-dlp cookiesfrombrowser — Brave is cross-platform and yt-dlp-native), and optional residential proxy fallback - see references/configuration.md. Key default: --per-channel-cap 3 (v1.3 behaviour change; pass 0 to restore legacy uncapped ranking).
Pre-flight: VPN Check (MANDATORY, runs before Phase 0)
Apply reference/vpn-preflight.md before any network operation in this skill.
In short:
-
Run a silent exit-IP check:
python -c "import urllib.request, json; r = urllib.request.urlopen('https://api.ipify.org?format=json', timeout=5); print(json.loads(r.read().decode())['ip'])" -
Geolocate via
https://ipinfo.io/<ip>/json-- look at theorgfield. -
Present the combined gate with AskUserQuestion:
Pre-flight check before
/yt-pulse. Current exit:<IP>(<ORG>,<COUNTRY>).- VPN: Confirm you are connected to Proton VPN (Amsterdam verified working) or a residential proxy. If you are on Mullvad or bare ISP, the transcript step will likely fall back to web search.
- Browser cookies: For the authenticated path, close the cookie-source browser (Brave by default) before proceeding. Chromium-family browsers lock their cookie SQLite DB on Windows while running, blocking yt-dlp from reading the ClaudeCode profile's YouTube session. Not fatal: the skill falls back to unauthenticated yt-dlp when locked. But closing it briefly enables the authenticated path and reduces bot-detection.
What ships with it
4 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.
- 9d ago First seen · 313 lines · 145 tokens per session scan A 286af1d4e0ca
yt-pulse is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 145 tokens to every session and 3,328 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.