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-launchgit 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-launch)<a href="https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-launch"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-launch/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-launch"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-launch.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 | $0.00092 | $0.00968 |
| Opus 5 | $0.00046 | $0.00484 |
| Sonnet 5 | $0.00018 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
liam-launch 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 10d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liam: guarded campaign launch
Everything Liam creates is a DRAFT and there is deliberately no activate tool, so the cost of a mistake is rework, not money. This skill's job is making rework rare: gather a complete brief, estimate before creating, apply the house rules, confirm, create, verify.
How to reach Liam
Prefer the liam MCP tools if loaded: launch_from_brief, create_campaign_group,
create_campaign, create_image_ad, search_targeting, list_targeting_facets,
estimate_audience, list_conversions, upload_audience_csv,
audience_from_salesforce. CLI fallback: liam launch --brief brief.json (see
examples/brief.json in the Liam repo). Naming map: campaignGroupName is LinkedIn's
"campaign", campaignName is the "ad group", creatives are the "ads".
Step 1: gather the brief
Required before anything is created: group and campaign names, daily budget and bid (with currency), landing URL, run start (epoch ms, must be in the future), the audience (a matched-list CSV, a Salesforce SOQL query, or targeting facets), and the ad copy or enough intent to draft it. Name entities so the angle is legible (persona, offer, competitor, audience in the name); the analysis skills mine angles from names later.
Step 2: resolve and estimate before creating
- Resolve targeting facets with
search_targeting; verify facet names withlist_targeting_facets(they are exact; job functions isjobFunctions, notfunctions). estimate_audienceon the resolved spec and quote the reach in the confirmation.- Matched audiences need ~300 members to serve at all; warn below that, and note matching takes up to 48h, so the run start should allow for it.
- CSV audiences: always
--dry-runfirst and show the cleaned columns and row count before uploading.
Step 3: apply the house rules
Ask once for the account's standing defaults if you do not know them, then apply on every campaign:
- Audience Expansion off and LinkedIn Audience Network off. Where Liam does not expose a toggle at creation, list it as a Campaign Manager check in the handoff rather than assuming.
- Standing exclusion audiences (customers, competitors, employees are the usual set) on every campaign.
- Conversion tracking wired: use the user's named conversion or the config
default (
conversionName/conversionIds;list_conversionsto look up). Never create a campaign that tracks nothing. - Format is create-only. A video campaign must be created with format SINGLE_VIDEO; format cannot be patched afterwards. Getting this wrong means recreating the campaign.
- Sponsoring somebody else's post takes the ENGAGEMENT objective.
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.
- 10d ago First seen · 79 lines · 92 tokens per session scan A 9b7230c30334
liam-launch is a skill published in the GitHub repository stan-rym/liam-linkedin-ads-MCP (22 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 968 once invoked, about $0.0005 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…