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 anhnguyen0905/codex-mcp --skill performance-marketinggit clone --depth 1 https://github.com/anhnguyen0905/codex-mcpWrote 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/anhnguyen0905/codex-mcp/performance-marketing)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/performance-marketing"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/performance-marketing/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/anhnguyen0905/codex-mcp/performance-marketing"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/performance-marketing.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 | $0.00953 |
| Opus 5 | $0.00034 | $0.00477 |
| Sonnet 5 | $0.00013 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
performance-marketing 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 10d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Marketing (paid acquisition diagnosis & optimization)
Decompose before you touch anything
Never optimize a moved metric directly — decompose it and find which factor actually moved:
CPI = CPM / 1000 ÷ (CTR × CVR_install)
CPA_purchase = CPI ÷ CVR_purchase
ROAS = revenue_attributed / spend
So "CPI +40%" is exactly one of: CPM rose (auction/competition/seasonality), CTR fell (creative fatigue, wrong audience), or CVR fell (store page, onboarding, tracking break, geo mix shift). Pull all three before proposing anything. If CPM rose while CTR/CVR held, the market changed and creative work is the wrong fix.
Diagnosis order
- Verify the measurement first. SDK/tracking break, attribution window change, or a reporting-lag artifact explains more "sudden" moves than real performance does.
- Check the mix. Aggregate CPI can rise while every campaign's CPI falls, if spend shifted to an expensive geo/placement (Simpson's paradox). Always segment by geo, placement, campaign, OS.
- Then look at creative and audience.
Creative fatigue
- Signals: CTR decaying vs its own first-72h baseline, frequency climbing (>2.5–3 on Meta for prospecting), CPM stable but CTR falling, spend concentrating on one ageing asset.
- Refresh when CTR drops ~20–30% from the asset's own baseline — not on a fixed calendar.
- Judge a creative only after enough impressions/conversions for stability; daily swings on a new asset are noise, and killing early is the most common way to starve a winner.
Bidding guardrails (tROAS / tCPA)
- Smart bidding needs a minimum conversion volume per week or it never leaves the learning phase; under that, consolidate campaigns instead of splitting them.
- Change one variable per learning window (typically 3–7 days). Stacked changes make the result uninterpretable.
- Target moves in small steps (±10–20%); a large tROAS jump collapses delivery.
- Every guardrail needs a floor and a ceiling: min spend to stay in learning, max CPI/CPA at which you pause.
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.
- 10d ago First seen · 86 lines · 67 tokens per session scan A fd3aba179787
performance-marketing is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 953 once invoked, about $0.0003 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…