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 krusemediallc/cursor-ad-agent --skill competitor-ad-researchgit clone --depth 1 https://github.com/krusemediallc/cursor-ad-agentWrote 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/krusemediallc/cursor-ad-agent/competitor-ad-research)<a href="https://agentmods.dev/skills/krusemediallc/cursor-ad-agent/competitor-ad-research"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/competitor-ad-research/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/krusemediallc/cursor-ad-agent/competitor-ad-research"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/competitor-ad-research.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 | $0.00122 | $0.02114 |
| Opus 5 | $0.00061 | $0.01057 |
| Sonnet 5 | $0.00024 | $0.00423 |
| Haiku 4.5 | $0.00012 | $0.00211 |
Grade A, and why
competitor-ad-research 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 12d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor ad research
Run a portable, auditable competitor workflow:
- Resolve exact Meta page identities.
- Pull all copy variants and useful delivery metadata.
- Optionally extract/download image and video creatives.
- Rank adaptation leverage from observable metadata.
- Optionally merge visual annotations backed by a local file.
- Write
BRIEF.mdwith local clone-skill handoffs.
Read reference.md for the data contract, page-confidence policy, fields, and score formula. Read annotations.md before creating annotations.
Hard rules
- Never guess a page. Accept a numeric ID,
Label=ID, a successful direct Facebook handle lookup, or one unique exact normalized Ad Library page-name match. If resolution is ambiguous or merely similar, stop for that page and ask for its numeric ID. - Keep credentials in
.env. UseMETA_ACCESS_TOKEN; never pass it on the command line, print it, or persist token-bearing snapshot URLs. - Deduplicate by Ad Library ID. Do not dedupe by copy, page, date, or creative URL.
- Preserve full copy. Keep every returned body, headline, description, and link-caption string without truncation.
- Call longevity a proxy, never performance. Commercial Ad Library longevity does not prove spend, conversions, ROAS, profitability, or a winning ad.
- Do not fabricate motifs. Name a motif only after visually inspecting the exact local creative. Every motif annotation needs
observed_fromplus concrete visibleevidence; the ranker enforces this. - Handoff local files only. Remote CDN or snapshot URLs are not clone inputs. Download first, then use paths emitted in
BRIEF.md. - Keep this workflow research-only. Do not generate or publish an ad until the user selects a source and separately invokes the relevant clone skill.
- Write only beneath
outputs/competitor-research/<run>/.
Preflight
From the repository root:
python3 --version
python3 -m pip install -r skills/competitor-ad-research/requirements.txt
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- annotations.md 3.9 KB
- reference.md 8.0 KB
- requirements-creatives.txt 47 B
- requirements.txt 23 B
- scripts/_common.py 9.3 KB runs code
- scripts/extract_creatives.py 23 KB runs code
- scripts/rank_competitors.py 27 KB runs code
- scripts/research_competitors.py 27 KB runs code
- tests/test_cli_contracts.py 11 KB runs code
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.
- 12d ago First seen · 232 lines · 122 tokens per session scan A 319d10c352e9
competitor-ad-research is a skill published in the GitHub repository krusemediallc/cursor-ad-agent (10 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 2,114 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
RunAPI Media Generator
A workflow for creating images, videos, music, and audio through RunAPI, a service that provides access to media-generation models. It checks the chosen model and request before submitting the job.
RunAPI Model Explorer
A RunAPI catalogue assistant that lists available AI models, explains their required inputs, and provides current pricing information.
imaginode
Generate AI images and videos through the Imaginode MCP server (imaginode.ai). Use when the user asks to create, generate or illustrate an image, picture, visual, thumbnail, or a short video clip, and the Imaginode MCP tools (generateimage, generatevideo, listmodels, getgenerationstatus) are available.
uni1-image-ad
Use when the user wants to generate a Meta/Facebook image ad with Luma uni-1 and attach it to an existing Meta ad set. Triggers on phrases like "uni-1 ad", "make a Luma ad creative", "new image ad in ", "uni-1 image ad for Meta", "generate uni-1 ad creative", "upload uni-1 image as Meta ad". Anchors on uni-1 + Meta…
image-ad-clone
Use when the user wants to reverse-engineer an existing image ad into a reusable, parameterizable prompt template that can be reused with any brand and any product. Triggers on phrases like "clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", "extract a template from this image"…
distribea-media
Generate or place on-brand media (images, video, music, voice) with Distribea. Use whenever a project needs imagery or audio — a hero/illustration/avatar, a page full of placeholders, a video clip, background music, or a voice-over — instead of shipping stock photos, placeholders, CSS-gradient-only sections, or raw…