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 kelpi-ai/meta-ads-skills --skill brand-readergit clone --depth 1 https://github.com/kelpi-ai/meta-ads-skillsWrote 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/kelpi-ai/meta-ads-skills/brand-reader)<a href="https://agentmods.dev/skills/kelpi-ai/meta-ads-skills/brand-reader"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/brand-reader/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/kelpi-ai/meta-ads-skills/brand-reader"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/brand-reader.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 | $0.00051 | $0.00442 |
| Opus 5.5 | $0.00020 | $0.00177 |
| Sonnet 5.5 | $0.00010 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
brand-reader 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.
What it actually says
Brand Reader
Doctrine
The kickoff call an agency bills for is mostly this: reading your website carefully. An ad that does not sound and look like the brand gets scrolled past as noise, and post-Andromeda the creative itself is what the delivery system aims with. The brand kit is the input to everything downstream.
When to use
- Before writing any angles or creative.
- When ads look like stock templates that could belong to anyone.
- Works with no MCP. If one is connected, the last step verifies the right Facebook Page.
Run it
Read [YOUR_WEBSITE_URL] and build me a brand kit:
1. The offer, in one sentence a stranger would understand.
2. Who it is clearly for (be specific: the customer the site is obviously written for).
3. Voice: 5 adjectives plus 3 short phrases lifted verbatim from the site that sound most like the brand.
4. Proof available: testimonials, numbers, named clients, guarantees. Quote them exactly; do not improve them.
5. Visual kit: brand colors (hex if visible in the CSS or brand pages), fonts, and how imagery is treated.
6. What the site is silent about that ads would need (price? shipping? guarantee?). List these as open questions, not guesses.
If I have a Meta Ads MCP connected, list my Facebook Pages so I can confirm which one these ads will run from.
Guardrails
- Quote proof verbatim. Never invent a testimonial, round a number, or upgrade "customers love us" into a statistic.
- Open questions stay open. The gaps list is the point; a guessed answer poisons every ad downstream.
Good output looks like
A one-page kit you could hand to a stranger who could then write an on-brand ad without visiting the site, plus an honest list of what is missing.
What ships with it
1 file 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.
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 · 37 lines · 51 tokens per session scan A df611f81a04c
brand-reader is a skill published in the GitHub repository kelpi-ai/meta-ads-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 442 once invoked, about $0.0002 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 2026-08-31.
brand-reader compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brand-readerkelpi-ai/meta-ads-skills | Skill | 5 | 4mo ago | MIT | A | 51 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |