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 competitor-scangit 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/competitor-scan)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/competitor-scan"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/competitor-scan/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/competitor-scan"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/competitor-scan.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 53 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00135 | $0.00996 |
| Opus 5 | $0.00068 | $0.00498 |
| Sonnet 5 | $0.00027 | $0.00199 |
| Haiku 4.5 | $0.00014 | $0.00100 |
Grade A, and why
competitor-scan 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 7d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Radar Setup
Turns "I want to track my competitors" into a live, self-refreshing, branded dashboard in one guided session. This skill sets up the machine; the competitor-radar skill is the machine.
Step 1: Discovery Q&A (interactive)
Ask, one topic at a time, adapting to answers:
- Niche / what they do (so competitor discovery and framing are accurate).
- Competitors, three modes:
- They name them, or
- They ask you to find and recommend competitors: search YouTube, the web, and their niche communities, propose 5-8 with a one-line why each, and let them confirm/trim, or
- A mix (they name a few, you fill the rest).
- Platforms to track: which of YouTube, Instagram, LinkedIn, TikTok, community (Skool/Circle), SEO. Only track what matters to their niche (a local business cares about Google reviews + local SEO; a creator cares about YouTube + shorts platforms).
- Brand: colors, fonts, logo. If they have a design system or a site, extract from it; else use sensible defaults and confirm.
- Cadence: weekly (default, Monday) or monthly (1st). And where to post it (Slack channel, email).
Write their answers into a config.json shaped like the competitor-radar skill's config (roster + platforms + apify_actors + brand + slack_channel + live_url + deploy_repo).
Step 2: Connect the data sources
Get the scrapers connected before building. See references/data-sources.md for the platform-to-actor mapping, Firecrawl and YouTube setup, and the avatar-inlining rule.
Step 3: Build the branded dashboard
Reuse the competitor-radar skill's assets/template.html + scripts/build_dashboard.py, restyled to their brand (swap the CSS color/font tokens, keep the structure: Demo/Actual tabs, per-platform columns, expand cards, focus/blur toggle, week-over-week deltas). Gather the first week of real data via the connectors, write radar_data.js, run the build, and open it for their approval before deploying. Inline avatars per the rule in references/data-sources.md.
What ships with it
2 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.
- 7d ago First seen · 56 lines · 135 tokens per session scan A 41f932af3398
competitor-scan is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 996 once invoked, about $0.0007 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 2026-09-05.
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.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
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.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
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.