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 naveedharri/benai-skills --skill title-ideationgit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/title-ideation)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/title-ideation"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/title-ideation/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/naveedharri/benai-skills/title-ideation"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/title-ideation.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 Memory Poisoning · line 43 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00173 | $0.01856 |
| Opus 5.5 | $0.00069 | $0.00742 |
| Sonnet 5.5 | $0.00035 | $0.00371 |
| Haiku 4.5 | $0.00017 | $0.00186 |
Grade A, and why
title-ideation 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 1mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Title Ideation, Two-Lens and Recent-Only
Produce a title shortlist grounded in the video and in fresh comp-set data: two option sets, topic-based and pattern-based. Background and history: references/design-notes.md (do not read at runtime).
Trigger
Run when Ben says "title ideation", "title angles", "title brainstorm", "title shortlist", "what should I call this video", "give me titles for X", or hands over a video idea, transcript, or reference videos and asks for titles.
Do NOT run for thumbnail design, full brief/outline, or weekly intel reports (dedicated skills exist).
Connectors
- YouTube connector:
searchVideos,getVideoDetails,getChannelStatistics,getTranscripts. - vidIQ MCP optional as fallback:
vidiq_channel_videoswithpopular: false,vidiq_get_videos_by_ids. Nevervidiq_outliers. - Every connector call runs inside a subagent, never in the main context (Phase 3).
Recency rule (non-negotiable)
- Last 20 to 25 long-form uploads per channel, ordered by date, capped to roughly the last 6 months. Exclude Shorts (
videoDuration: long). If a channel posts rarely, keep 25 but note the dates and weight it lower. - Rank by views-per-day or views-vs-channel-average, never raw views. Weight a subject or pattern by recurrence across channels AND climb speed.
Workflow
Use TaskCreate to expose the phases.
Phase 1, Intake
Get the topic, Ben's take, and optional inputs (transcript IDs, reference URLs, constraints, planned runtime). If something critical is ambiguous, use AskUserQuestion once.
Phase 2, Load context (silent)
Read Context/brand.md, Context/icp.md, Context/strategy.md if present, latest daily note if any. These are small, read them directly.
If Ben shared transcript IDs or reference URLs, do NOT pull them inline. Spawn a subagent (batched with Phase 3's agents) that calls fireflies_get_summary / getTranscripts / getVideoDetails and returns core claims, strongest moments, and anything title-relevant in 10 lines or fewer.
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.
- 1mo ago Changed · +1 lines 33f2bbf5b03f
- 1mo ago First seen · 107 lines · 173 tokens per session scan A 31e90ceedf27
title-ideation is a skill published in the GitHub repository naveedharri/benai-skills (74 stars, last pushed 16d ago), licensed MIT. It adds 173 tokens to every session and 1,856 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.
setup-mcp-connector
A step-by-step setup guide for connecting Cowork to services such as Google Drive, Notion, and Higgsfield, plus Korean public-data, document, statistics, architecture, and law services. It explains authentication, API keys, test calls, and troubleshooting.
media-gpt-image-prompt
An image-prompt writing tool that turns a natural-language idea into detailed prompts for GPT Image 2.5. It can also adapt the same idea for Gemini 3 Pro Image and Midjourney.