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 mergisi/awesome-hermes-agent --skill competitor-landing-watchgit clone --depth 1 https://github.com/mergisi/awesome-hermes-agentWrote 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/mergisi/awesome-hermes-agent/competitor-landing-watch)<a href="https://agentmods.dev/skills/mergisi/awesome-hermes-agent/competitor-landing-watch"><img src="https://agentmods.dev/badge/skills/mergisi/awesome-hermes-agent/competitor-landing-watch/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/mergisi/awesome-hermes-agent/competitor-landing-watch"><img src="https://agentmods.dev/badge/skills/mergisi/awesome-hermes-agent/competitor-landing-watch.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 | $0.00029 | $0.01394 |
| Opus 5 | $0.00015 | $0.00697 |
| Sonnet 5 | $0.00006 | $0.00279 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
competitor-landing-watch 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Landing Watch
Daily snapshot + diff of competitor landing pages. Catches pricing changes the same day they happen, new feature claims, hero copy swaps, and quiet pages that go silent. Filters out the noise (deploy hashes, JS asset URLs, copyright year bumps) so you only see signal.
What this skill does
Once a day (default 6am):
- Fetch each competitor URL in your watchlist.
- Extract the meaningful content — strip JS bundle hashes, ignore Cloudflare/CDN footer text, normalize whitespace, keep
<h1>-<h3>headings, hero/sub-hero copy, pricing blocks, feature lists, CTA button text. - Diff against yesterday's snapshot — semantic diff, not character-level. "Pro plan went from $49 to $59" beats "12 chars changed."
- Classify each change by importance:
- High — pricing, plan structure, new feature claim, removed feature, CTA change
- Medium — hero copy, social proof additions, new logos
- Low — minor wording, marketing copy nudges
- Surface only High + Medium in the daily digest. Low changes are logged but suppressed.
- Post to Slack/Discord/Telegram — formatted as a per-competitor section with the change quoted and a link to the page.
- Weekly rollup — every Friday, a "what shifted this week across all competitors" summary.
What this skill does NOT do
- It does NOT scrape login-gated pages. If a competitor's pricing is behind a "Talk to sales" wall, this skill can't see it.
- It does NOT do trademark monitoring or aggressive content scraping at scale. Default config respects robots.txt and waits 2 seconds between fetches.
- It does NOT replace a real CI tool like Crayon or Klue for enterprise teams. This is the lightweight version for solo founders and 2-person sales teams.
- It does NOT analyze your own product positioning — it watches competitors. Use a separate skill for self-audit.
How to invoke
Scheduled (recommended):
/cron daily "every day at 6am, run /competitor-landing-watch"
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 · 130 lines · 29 tokens per session scan A 54b995e96fd3
competitor-landing-watch is a skill published in the GitHub repository mergisi/awesome-hermes-agent (2 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,394 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
unity-agent-workflows
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…
interpreting-mod-author-instructions
A guide for following a Bethesda mod author's installation instructions, including file choices, prerequisites, and installer options.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
using-bgs-archive
Use when the user wants to inspect, list, extract, unpack, or repack Bethesda BA2/BSA archives; determine archive format/version/compression; or build archive assets for an MO2 overlay. Triggers - "unpack BA2", "extract BSA", "pack archive", "inspect archive", "bgs-archive".
docker-patterns
Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.
context-engineering
A project documentation framework that records a project's goals, requirements, roadmap, and current state in separate files. It also keeps those documents within set size limits for an AI coding agent.