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-weeklygit 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-weekly)<a href="https://agentmods.dev/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly/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-weekly"><img src="https://agentmods.dev/badge/skills/stan-rym/liam-linkedin-ads-mcp/liam-weekly.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 | $0.00080 | $0.00726 |
| Opus 5.5 | $0.00032 | $0.00290 |
| Sonnet 5.5 | $0.00016 | $0.00145 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
liam-weekly 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 2mo 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: weekly snapshot
A snapshot, not a report. The same shape every week so weeks are comparable at a glance, short enough to read in a Slack message. Target under 40 lines of output.
How to reach Liam
Prefer the liam MCP tools if they are loaded. This skill wants two exact 7-day
windows, so use get_performance with explicit startDate/endDate (YYYY-MM-DD):
the last 7 full days, and the 7 before those. On the CLI, liam report summary -p last_7_days plus liam report trend <level> <id> -b weekly approximates it. Also pull
list_campaigns (structure and statuses), list_ads on active campaigns if ad-level
movers are wanted, and list_ad_changes for what was changed this week. Read-only.
What goes in
- Scoreboard: spend, impressions, CTR, conversions, cost per conversion for this week, each with the week-over-week delta.
- Movers: entities whose CTR, spend, or cost per conversion moved more than ~20% week over week, on at least ~1,000 impressions in both weeks. Cap at 3 up, 3 down.
- New this week: ads or campaigns that appeared (from
list_campaigns/list_ads), and journaled changes (list_ad_changes) so the reader connects moves to outcomes. - Flags: ACTIVE campaigns with zero delivery, audiences still matching or under 300 members, creatives with CTR down two-plus weeks running, conversion counts likely still lagging for the last 2 days.
- Do this week: at most 3 actions, imperative, each tied to a number above.
Rules
- Same section order every week; never add sections ad hoc.
- Deltas as signed percentages; money in account currency.
- No verdicts on entities below the volume floor; skip them silently here (the deep dives are liam-performance and liam-leads, and the snapshot should say so only when something big warrants it).
- If the week was quiet, say it in one line and keep the snapshot short rather than inflating noise into findings.
Report format
LinkedIn ads, <start> to <end>
Spend $X (+Y%) | Leads N (+Y%) | CPL $X (+Y%) | CTR X% (+Y%)
Up: ...
Down: ...
New: ...
Flags: ...
Do this week:
1. ...
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.
- 2mo ago First seen · 66 lines · 80 tokens per session scan A 7d66c0f3461e
liam-weekly is a skill published in the GitHub repository stan-rym/liam-linkedin-ads-MCP (23 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 726 once invoked, about $0.0003 per session on Opus 5.5. 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.
liam-weekly compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| liam-weeklystan-rym/liam-linkedin-ads-MCP | Skill | 23 | 2mo ago | MIT | A | 80 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | yesterday | MIT | A | 95 | Claude Code |