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 copy-formulasgit 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/copy-formulas)<a href="https://agentmods.dev/skills/kelpi-ai/meta-ads-skills/copy-formulas"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/copy-formulas/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/copy-formulas"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/copy-formulas.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 | $0.00695 |
| Opus 5.5 | $0.00027 | $0.00278 |
| Sonnet 5.5 | $0.00013 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
copy-formulas 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Formulas
Doctrine
Copywriting formulas are not templates to fill; they are conversion-ordered thinking. PAS works because naming a pain earns attention honestly. Before-After-Bridge works because people buy the after, not the product. The formula's job is to keep you from burying the promise under cleverness. Rule of placement: Meta primary text has one job (stop the scroll and earn the click), so pain-first formulas (PAS, SCQA, Before-After-Bridge) usually beat feature-first ones (FAB) for cold audiences. Story formulas (Star-Story-Solution, long storytelling) earn their length only in retargeting or founder-voice posts.
When to use
- Drafting primary text for a new angle (feed it the angle's WHO, PAIN, PROMISE).
- Diagnosing copy that gets glanced at but not clicked: it is usually a formula with a missing step.
- Works with no MCP.
Run it
Write ad copy for this angle:
WHO: [from Angle Writer] PAIN: [verbatim if possible] PROMISE: [from Pain to Promise]
Placement: [Meta primary text (cold) / retargeting / landing page hero]
Voice: [3 adjectives + one verbatim brand phrase]
1. Pick the 2 best-fit formulas for this placement and say why in one line each. Choose from: PAS (pain, agitate, solve), AIDA, Before-After-Bridge, 4Ps (promise, picture, proof, push), SCQA (situation, complication, question, answer), Star-Story-Solution, PPPP (problem, promise, proof, proposal), straight storytelling.
2. Write one version per formula. Meta primary text: first line must work standalone (it is all most people see before "...more"), under 125 words total, no hashtags, one CTA.
3. Label each structural beat inline in a copy of the draft (so I can see the formula working).
4. PROOF beats use only real proof I gave you. If I gave none, write the version without a proof beat and tell me the copy is weaker until I supply it.
5. If I pasted EXISTING copy instead: name the formula it is closest to, the beat it is missing or burying, and rewrite it with the missing beat restored.
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 · 39 lines · 67 tokens per session scan A a06d91f0c082
copy-formulas is a skill published in the GitHub repository kelpi-ai/meta-ads-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 695 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 2026-08-31.
copy-formulas compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| copy-formulaskelpi-ai/meta-ads-skills | Skill | 5 | 4mo ago | MIT | A | 67 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |