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 stan-rym/liam-linkedin-ads-MCP --skill liam-competitorsgit clone --depth 1 https://github.com/stan-rym/liam-linkedin-ads-MCPWrote 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/stan-rym/liam-linkedin-ads-mcp/liam-competitors)<a href="https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-competitors"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-competitors/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/stan-rym/liam-linkedin-ads-mcp/liam-competitors"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-competitors.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 | $0.00084 | $0.00803 |
| Opus 5 | $0.00042 | $0.00402 |
| Sonnet 5 | $0.00017 | $0.00161 |
| Haiku 4.5 | $0.00008 | $0.00080 |
Grade A, and why
liam-competitors 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 12d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liam: competitor ad research
The deliverable is a strategy read, never the ad list itself. Read the copy, formats, targeting, and cadence, then explain how the competitor runs their account and what that means for the user's own ads.
How to reach Liam
Prefer the liam MCP tool inspect_competitor_ads if loaded. Otherwise the CLI:
liam competitor ads <advertiser> (or node <liam-repo>/packages/cli/dist/index.js competitor ads ...). No ad-account access is needed; this reads the public LinkedIn
Ad Library.
Getting the right ads
- Name vs company id. A name search is broad and pulls in partners and resellers
("HubSpot" also returns HubSpot solution partners). For exactly one company's ads,
use the numeric company id or a
linkedin.com/company/<id>URL (scraper engine), or post-filter API results by the advertiser/payer field. - Engines.
auto(default) uses the official API for metadata and layers ad copy from each ad's detail page;apiis metadata-only but fast and works without a local browser (the only engine on a hosted MCP);scraperdrives a local Chrome and gets copy without the API grant. - Volume. Default cap is 50 ads; raise
--maxfor big advertisers (the API reports the advertiser-wide total, quote it for context). Deep copy fetches cost a detail-page visit per ad, so very large pulls take minutes. - EU bonus data. Ads served in the EU carry run dates, impression ranges, per-country splits, and structured targeting facets. Use them; they are the closest thing to seeing a competitor's media plan.
Synthesis framework
Work through these dimensions and ground every claim in specific ads (quote short copy snippets):
- Messaging themes. The 2-4 recurring value props or narratives across the ads.
- Offers and CTAs. What they ask for: demo, trial, report, webinar, event. The offer mix reveals which funnel stage they are buying.
- Format mix. Single image vs video vs carousel vs document vs thought-leader ads, roughly proportioned.
- Who they spotlight. Executives, customers, partners, product screenshots.
- Cadence and scale. How many ads run concurrently, how often new ones ship (run dates where available), impression volume and geography.
- Targeting (EU data where present): languages, locations, company and job facets, notable exclusions.
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.
- 12d ago First seen · 66 lines · 84 tokens per session scan A a276b253b0fe
liam-competitors is a skill published in the GitHub repository stan-rym/liam-linkedin-ads-MCP (22 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 803 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…