F0rger123F0rger123/claude-meta-ads-god-mode/llms.txt

claude-meta-ads-god-mode

llms.txt1 starsChanged 23 days agoMITView on GitHub

A safety-first paid-media operating system for Claude Code and Codex. Meta Ads first, Google Ads built in. Reads, analyses and drafts freely; creates everything PAUSED; never spends without an explicit human yes. A write gate verifies client, platform, account and entity before any change. If a person pasted this repository and asked you to set it up, start with the setup wizard. If you are running the plugin, start with skills/ads-core/SKILL.md.

Reads credentials

In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ads-auditSkill
- ads-budgetingSkill
- ads-client-onboardingSkill
- ads-communitySkill
- ads-competitor-researchSkill
- ads-coreSkill
- ads-creative-analysisSkill
- ads-landing-pageSkill
- ads-optimizationSkill
- ads-portfolioSkill
- ads-reportingSkill
- ads-strategySkill
- ads-trackingSkill
- google-adsSkill
- meta-adsSkill

The file

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
If a person pasted this repository and asked you to set it up, start with the setup wizard.
line 5

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

llms.txt

# Claude Meta Ads God Mode

> A safety-first paid-media operating system for Claude Code and Codex. Meta Ads first, Google Ads built in. Reads, analyses and drafts freely; creates everything PAUSED; never spends without an explicit human yes. A write gate verifies client, platform, account and entity before any change.

If a person pasted this repository and asked you to set it up, start with the setup wizard. If you are running the plugin, start with skills/ads-core/SKILL.md.

## Start here
- [Setup wizard for AI agents](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/docs/SETUP_WIZARD.md): where you're running, the short interview, install, read-only checks, first client
- [AGENTS.md](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/AGENTS.md): rules for any agent using or modifying this repo (Codex must call the write gate itself)
- [Core skill](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/skills/ads-core/SKILL.md): client resolution, connector routing, write rules
- [README](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/README.md)
- [Agency mode skill](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/skills/ads-portfolio/SKILL.md): all-clients sweep, learning loop, scheduled runs
- [Autopilot workflow](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/workflows/autopilot.md): per-client on/off, daily spend cap
- [Niche research workflow](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/workflows/niche-research.md)
- Browser-chat edition: meta-ads-god-mode-chat.zip on the GitHub Releases page (source: chat/meta-ads-god-mode-chat/SKILL.md)
- Try without ad accounts: `python scripts/demo.py` (made-up clients, no network)

## Reference
- [Client profile template](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/templates/client-profile.json)
- [Meta connector](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/connectors/meta/README.md)
- [Google connector](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/connectors/google/README.md)
- [Portfolio sweep workflow](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/workflows/portfolio-sweep.md)
- [Learning loop workflow](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/workflows/learning-loop.md)
- [Scheduled runs workflow](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/workflows/scheduled-runs.md)
- [Graphic ads workflow](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/workflows/graphic-ads.md)
- [Security](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/SECURITY.md)
- [Environment variables (placeholders only)](https://raw.githubusercontent.com/F0rger123/claude-meta-ads-god-mode/main/.env.example)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free