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 fatigue-detectorgit 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/fatigue-detector)<a href="https://agentmods.dev/skills/kelpi-ai/meta-ads-skills/fatigue-detector"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/fatigue-detector/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/fatigue-detector"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/fatigue-detector.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 | $0.00044 | $0.00514 |
| Opus 5 | $0.00022 | $0.00257 |
| Sonnet 5 | $0.00009 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
fatigue-detector 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 11d 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
Fatigue Detector
Doctrine
"CTR down, CPM up, must be fatigue" is the most common misdiagnosis in ads. Sometimes it is the auction, the season, or a broken pixel. The two-condition rule cuts false alarms: an ad is fatigued only when frequency > 4.0 AND CTR is down 30%+ from its own baseline. Post-Andromeda, ad lifespans compressed and fatigue scales with spend more than with days, so small budgets fatigue slower than the "20 new ads a month" crowd claims. The owner's version of this pain: "the exact same ads that cost $6.85 a lead now cost $30.90."
When to use
- A previously-working ad got expensive.
- Before killing anything: impatience kills more winners than fatigue does.
- Needs a Meta Ads MCP, read access.
Run it
Fatigue check, READ-ONLY, change nothing:
1. Pull frequency and CTR by ad for the last 14 days, plus each ad's CTR baseline from its best prior 14-day window.
2. Apply the two-condition rule: flag ONLY ads with frequency > 4.0 AND CTR down 30%+ from their own baseline.
3. For each flagged ad: which angle is it, how much has it spent since the decline started, and is a sibling angle still healthy?
4. For ads that LOOK tired but fail the rule: tell me the likelier cause (auction/CPM shift, seasonality, tracking change, or not enough recent spend to judge).
5. Recommend per flagged ad: refresh the creative (same angle, new execution) or retire the angle (the message is exhausted, not the image). Do not touch anything.
Guardrails
- Read-only. Refresh and retire are human decisions.
- Never judge an ad against another ad's baseline; fatigue is measured against the ad's own history.
- A new execution of a dead angle is still dead. If three executions of one angle all decayed fast, the angle is done: back to Angle Writer.
Good output looks like
A short list split into "actually fatigued (here is the evidence)" and "leave it alone (here is what is really happening)".
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.
- 11d ago First seen · 35 lines · 44 tokens per session scan A a857ab00b0af
fatigue-detector is a skill published in the GitHub repository kelpi-ai/meta-ads-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 514 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…