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 citedy/adclaw --skill ads-competitorgit clone --depth 1 https://github.com/citedy/adclawWrote 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/citedy/adclaw/ads-competitor)<a href="https://agentmods.dev/skills/citedy/adclaw/ads-competitor"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/ads-competitor/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/citedy/adclaw/ads-competitor"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/ads-competitor.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 | $0.00067 | $0.01338 |
| Opus 5.5 | $0.00027 | $0.00535 |
| Sonnet 5.5 | $0.00013 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
ads-competitor 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.
This is a copy
98% identical to ads-competitor — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Ad Intelligence
Process
- Identify target competitors (from user input or industry analysis)
- Read
ads-shared/references/benchmarks.mdfor industry CPC/CTR/CVR baselines - Research competitor ad presence across platforms
- Analyze ad copy, creative, and messaging themes
- Estimate competitor spend and keyword strategy
- Identify gaps and opportunities
- Generate competitive intelligence report
Data Sources
Free Intelligence Sources
| Source | Platform | What You Can Find |
|---|---|---|
| Google Ads Transparency Center | Active ads, formats, geo targeting | |
| Meta Ad Library | Meta/Instagram | All active ads, creative, copy, spend range |
| LinkedIn Ad Library | Active ads from company pages | |
| TikTok Creative Center | TikTok | Top ads, trending creative, hashtags |
| Microsoft Ads | Microsoft | Limited: use auction insights |
Google Ads Auction Insights
Available from the user's own Google Ads account:
- Impression share vs competitors
- Overlap rate (how often you compete)
- Outranking share (who wins more often)
- Top of page rate and absolute top of page rate
- Available for Search and Shopping campaigns
Platform-Specific Research
- Ads Transparency Center: search by advertiser name or domain
- Search for competitor brand terms to see their ads live
- Auction Insights for impression share comparison
Meta
- Ad Library: filter by advertiser, country, platform (FB/IG), date range
- Shows creative (image/video), ad copy, active dates
- Shows platform placement (Facebook, Instagram, Audience Network)
- Ad Library: search by company name
- Shows Sponsored Content, Message Ads
- Limited data compared to Meta Ad Library
TikTok
- Creative Center: top-performing ads by industry, country, objective
- Hashtag analytics: trending sounds and hashtags
- No per-advertiser library; use Creative Center for industry trends
Competitive Analysis Framework
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 · 157 lines · 67 tokens per session scan A 4da35d408e55
ads-competitor is a skill published in the GitHub repository citedy/adclaw (49 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,338 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to ads-competitor, differing in 18 lines, and is treated as a copy.
ads-competitor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ads-competitorcitedy/adclaw | Skill | 49 | 3mo ago | Apache-2.0 | A | 67 | Claude Code, Codex |
| skill-creatorHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 13 | Claude Code, Codex |
| cronHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 8 | Claude Code, Codex |
| tmuxHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 20 | Claude Code, Codex |
| weatherHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 8 | Claude Code, Codex |
| clawhubHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 19 | Claude Code, Codex |
| githubHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 19 | Claude Code, Codex |