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-performancegit 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-performance)<a href="https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-performance"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-performance/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-performance"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-performance.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 | $0.00876 |
| Opus 5 | $0.00038 | $0.00438 |
| Sonnet 5 | $0.00015 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
liam-performance 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liam: performance review
Produce a review a growth lead could act on in ten minutes: verdict, winners, losers, watchlist, actions. Every claim grounded in a number.
How to reach Liam
Prefer the liam MCP tools if they are loaded (performance_summary, get_performance,
performance_trend, list_campaigns, list_ads). Otherwise the CLI: liam report ...,
or node <liam-repo>/packages/cli/dist/index.js if not globally linked. CLI presets cap
at 90 days; for custom windows use the MCP tools with startDate/endDate. Read-only.
Scope
Default to the whole account over last_30_days. If the user names a campaign group,
campaign, or period, scope to it. If total conversions in the window are under ~10,
widen to last_90_days and say you did.
What to pull
performance_summaryfor the rollup, top/bottom performers, and flags.get_performanceatcampaign_group,campaign, andcreativelevels.performance_trend(weekly) on the account and on the top 2-3 spend campaigns.list_campaignsto map ids to names/statuses and to catch ACTIVE entities with no delivery (drafts are expected to be absent; actives are not).
KPI framework
Judge in this order, and never let an upstream metric excuse a downstream one:
- Delivery: impressions, spend. Nothing else matters if it is not serving.
- Engagement: CTR, CPC. Is the creative earning the click?
- Outcome: conversions, conversion rate, cost per conversion. The only layer that pays rent. An ad with a great CTR and no conversions is a pause candidate, not a winner.
Compare within the account first: compute account averages for CTR, CPC, and cost per conversion and measure each entity against them. Industry context only as rough guide rails (LinkedIn B2B single-image ads: CTR ~0.4-0.6%, CPC ~$8-16, CPM ~$30-60; lead-gen cost per conversion varies too much to benchmark honestly).
Judgment rules
- Significance floor: no winner/loser verdicts on creatives under ~1,000 impressions or ~3 conversions. Bucket them as "too early".
- Fatigue: CTR falling two or more consecutive weeks on unchanged creative and
targeting means the creative is wearing out. The fix on LinkedIn is recreate, not
edit: Campaign Manager ignores post edits, so copy changes are
delete_ad+create_image_ad(as new drafts). - Recency: conversions lag; exclude or caveat the last 2-3 days.
- If the account journal has entries (
list_ad_changes), check whether recent moves line up with metric shifts, and mentioncompute_liftfor a before/after read.
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 · 71 lines · 76 tokens per session scan A 33e7bf1d5f37
liam-performance 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 876 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…