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 pain-to-promisegit 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/pain-to-promise)<a href="https://agentmods.dev/skills/kelpi-ai/meta-ads-skills/pain-to-promise"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/pain-to-promise/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/pain-to-promise"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/pain-to-promise.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 | $0.00046 | $0.00601 |
| Opus 5.5 | $0.00018 | $0.00240 |
| Sonnet 5.5 | $0.00009 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
pain-to-promise 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pain to Promise
Doctrine
An angle lives or dies on its promise line, and promises fail in one predictable way: they generalize. "Essential nutrients in every bottle" is a promise to everyone, which the delivery algorithm reads as a promise to no one. "Lose weight without giving up the nutrients" names the person, the pain, and the outcome in nine words, so both the human and the algorithm know exactly who it is for. The narrower the promise, the harder it hits, and post-Andromeda, the better it delivers. New brands carry an extra burden: a stranger's promise needs specificity to be believed at all. Say how, say for whom, say what happens if it fails.
When to use
- Between Buyer Language Miner (the pain) and Angle Writer / Creative Director (the copy and image).
- When an ad gets impressions but no clicks: usually a promise problem.
- Works with no MCP.
Run it
Turn these pains into promises for my offer: [ONE-LINE OFFER]
Pains (verbatim, from my buyer language mining): [PASTE 3-5 PAIN QUOTES with WHO said each]
For each pain:
1. Flip it into 3 candidate promise lines. Each must name or unmistakably imply: the WHO, the pain, and the specific outcome. Under 12 words each.
2. Run the one-second test on each: would the person who said this pain, scrolling at speed, recognize this line as "for me" in one second? Kill any line where the honest answer is no.
3. Run the anyone-test: could a competitor, or a company in a different category, run this exact line? If yes, it is generic. Sharpen or kill.
4. For the surviving lines: state the believability load. What would a stranger need to see next to believe this (mechanism, proof, guarantee)? One line each.
5. Rank the survivors and tell me which single promise you would put $20/day behind first, and why.
Guardrails
- The promise must be one the offer actually keeps. A sharpened lie is still a lie; check every survivor against what the product really does.
- No superlatives without a mechanism ("the best" is noise; "the only one that X" must be true).
- Specific beats clever. If a line is witty but fails the one-second test, it is a caption, not a promise.
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 · 38 lines · 46 tokens per session scan A 8ff2d6cf50ad
pain-to-promise is a skill published in the GitHub repository kelpi-ai/meta-ads-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 601 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.
pain-to-promise compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pain-to-promisekelpi-ai/meta-ads-skills | Skill | 5 | 4mo ago | MIT | A | 46 | 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 |