agentleFS
Sign inStart free
F0rger123F0rger123/claude-meta-ads-god-mode/CLAUDE.md

claude-meta-ads-god-mode

CLAUDE.md1 starsChanged 23 days agoMITView on GitHub

This repo is a Claude Code plugin (ads) that operates real ad accounts. Two audiences use these instructions: Claude running the plugin (start at skills/ads-core/SKILL.md) and Claude developing the plugin (this file). Resolve the client -> adsgm use -> read -> plan (adsgm plan) -> show summary -> write -> read back. Create PAUSED. Spend only with approval.

The file

We split this CLAUDE.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Run python tests/run_all.py after every change.

    line 8
  2. Very specific:

    Never add credentials, real account ids, client names with real data, or anything from ~/.ads-godmode/ to the repo.

    line 9
  3. Very specific:

    Keep SKILL.md files lean (progressive disclosure).

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

CLAUDE.md - working on this repository

This repo is a Claude Code plugin (ads) that operates real ad accounts. Two audiences use these instructions: Claude running the plugin (start at skills/ads-core/SKILL.md) and Claude developing the plugin (this file).

Developing

  • Layout: skills/ (SKILL.md + references/workflows), workflows/, references/, templates/, commands/ (slash commands /ads:*), hooks/ (write gate), godmode/ (stdlib safety core + adsgm CLI), connectors/ (adapters, registry, Google writer), bundles/ (bundled companion plugins) and community/ (vendored third-party skills) - never edit either by hand; bump the pin in community/sources.json and run scripts/sync_community.py then scripts/build_catalog.py. Routing rules: community/router_rules.json (every pick must exist in the catalog). .codex-plugin/ + .agents/plugins/ make the repo a Codex plugin marketplace. tests/.
  • Run python tests/run_all.py after every change. All suites must pass; they need no network.
  • Never add credentials, real account ids, client names with real data, or anything from ~/.ads-godmode/ to the repo.
  • Safety code fails closed. New tool -> registry rule + test. Do not widen ALWAYS_BLOCKED/ALWAYS_APPROVAL exceptions without a test and a reason.
  • Keep SKILL.md files lean (progressive disclosure); depth goes in references.
  • Label knowledge (PLATFORM FACT with source + date / BEST PRACTICE / HEURISTIC / EXPERIMENT / CLIENT-SPECIFIC RULE). Never promise ad results.
  • Match the surrounding style: small modules, docstrings that explain why, JSON output from the CLI.

Running (summary - the skill is authoritative)

Resolve the client -> adsgm use -> read -> plan (adsgm plan) -> show summary -> write -> read back. Create PAUSED. Spend only with approval.

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