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-account-auditgit 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-account-audit)<a href="https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-account-audit"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-account-audit/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-account-audit"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-account-audit.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 | $0.00076 | $0.00643 |
| Opus 5 | $0.00038 | $0.00321 |
| Sonnet 5 | $0.00015 | $0.00129 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
liam-account-audit 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liam: account audit
A setup review, not a performance review (that is liam-performance). The output is a scorecard: pass, flag, or fail per area, each verdict carrying its evidence, followed by a ranked fix list. Run it quarterly or when inheriting an account.
How to reach Liam
Prefer the liam MCP tools: list_campaigns (drafts included), list_ads,
list_conversions, list_ad_changes, and a light get_performance pass to see what
is actually spending. Where Liam does not expose a field (some toggles and
associations are only visible in Campaign Manager), put it on the manual checklist at
the end rather than skipping it silently.
Areas
- Structure and naming. Does the tree read sensibly at each level? Do names encode audience, persona, or offer (the analysis skills mine angles from names, so opaque names cost real capability)? Duplicated or near-duplicate campaigns, archived clutter.
- Draft debt. Draft groups, campaigns, and ads older than ~2 weeks. Ship them or delete them; stale drafts hide real intent.
- Conversion wiring.
list_conversionsfor what exists; every active campaign should be associated with the right conversion. Campaigns tracking nothing, or tracking a legacy conversion, are flags. Multiple near-duplicate conversions in the account are themselves a flag. - Safety toggles. Audience Expansion off and Audience Network off is the sane default for targeted B2B accounts; confirm where readable, otherwise send to the manual checklist.
- Targeting overlap. Active campaigns whose targeting resolves to substantially the same audience bid against each other in the auction. List overlapping pairs and which one should own the audience.
- Landing pages and UTMs. Ad landing URLs resolve, use https, and carry consistent UTM parameters (source, medium, campaign) so downstream attribution holds. Inconsistent or missing UTMs on some ads is the most common silent leak.
- Journal coverage. Entities with meaningful spend but no journaled changes mean edits are happening untracked (usually directly in Campaign Manager); recommend the liam-experiments logging discipline.
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 · 51 lines · 76 tokens per session scan A d68f9fa410b9
liam-account-audit is a skill published in the GitHub repository stan-rym/liam-linkedin-ads-MCP (22 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 643 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…