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-experimentsgit 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-experiments)<a href="https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-experiments"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-experiments/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-experiments"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-experiments.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 | $0.00075 | $0.00690 |
| Opus 5 | $0.00037 | $0.00345 |
| Sonnet 5 | $0.00015 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
liam-experiments 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liam: experiments and lift
Ad accounts accumulate changes nobody can evaluate later because nobody wrote down what changed and why. Liam journals every change it makes automatically; this skill adds the discipline around it: hypotheses going in, honest verdicts coming out.
How to reach Liam
Prefer the liam MCP tools if loaded: log_ad_change, list_ad_changes,
compute_lift. CLI: liam changelog list, liam changelog add, liam lift <level> <entityId> [-w days]. The journal lives at ~/.liads/changelog.jsonl. Changes made
directly in Campaign Manager are invisible until logged by hand; that is the most
common reason a lift read comes back empty.
Starting a test
- Hypothesis first, one sentence: "outcome-led headline will beat feature-led on cost per conversion."
- Make the change. Copy changes on LinkedIn are recreate, not edit
(
delete_ad+create_image_ad, drafts, user confirms deletes); Liam journals these automatically. Changes made in Campaign Manager getlog_ad_changewith the entity, field, and after-value. - Label it (
-l "outcome-led headline test") and tag related changes so the test reads as one unit. - One change per entity at a time where possible. Two simultaneous changes on the same entity cannot be separated afterwards; if it happened anyway, say so in the read-out.
Reading a test
compute_lift compares the window before each recorded change against the same
window after (default 14 days) and reports per-metric deltas: CTR, CPC, conversions,
conversion rate, cost per conversion.
Rules for an honest read:
- Wait for volume, not just days. No verdict without ~1,000 impressions or a few conversions on each side; otherwise report "inconclusive, recheck on ".
- A
partialafter-window means the change is recent; present it as interim. - State the confounds every time: seasonality, LinkedIn's learning phase restarting after an edit (early post-change days usually dip), concurrent budget or audience changes. This is a directional pre/post comparison, never proof.
- Verdicts are exactly one of: better, worse, inconclusive.
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.
- 9d ago First seen · 61 lines · 75 tokens per session scan A 05a420e586d1
liam-experiments is a skill published in the GitHub repository stan-rym/liam-linkedin-ads-MCP (22 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 690 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…