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 agentmods add instructions/klosk/adloop/claude-mdgit clone --depth 1 https://github.com/kLOsk/adloopWhat 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 | $0.00796 | $0.00796 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
adloop CLAUDE.md 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AdLoop
MCP server connecting Google Ads + GA4 into one AI-driven feedback loop inside your IDE.
Quick Reference
uv sync # Install dependencies
uv run adloop init # Interactive setup wizard
uv run adloop # Start MCP server
pytest # Run tests
python scripts/sync-rules.py # Sync rules: .cursor/rules/ -> .claude/rules/
Architecture
src/adloop/
├── __init__.py # Entry point — routes 'adloop init' vs MCP server
├── server.py # FastMCP server — all tool registrations + toolset tags
├── config.py # Config loader (~/.adloop/config.yaml)
├── auth.py # OAuth 2.0 (user-supplied credentials, headless fallback) + service accounts
├── cli.py # Interactive setup wizard (own Google Cloud project + auto-discovery)
├── crossref.py # Cross-reference tools (GA4 + Ads combined)
├── tracking.py # Tracking validation + code generation
├── ga4/ # GA4 Data + Admin API (reports, realtime, events)
├── ads/ # Google Ads API (read, write, GAQL, forecasting, PMax, recommendations)
└── safety/ # Guards, previews, audit logging
Orchestration Rules
All tool usage rules, safety protocols, orchestration patterns, GAQL reference, GDPR awareness, and marketing best practices live in a single canonical file:
Read and follow .claude/rules/adloop.md for all AdLoop MCP tool orchestration.
That file is the complete guide for combining AdLoop's tools. It covers:
- Tool inventory with parameters and when to use each
- 9 safety rules (budget caps, dry-run defaults, Broad Match prevention, pre-write validation)
- 16 orchestration patterns (performance review, PMax analysis, recommendations, ad creation, tracking diagnosis, etc.)
- GAQL quick reference with syntax, common queries, and gotchas
- GDPR consent awareness for EU markets
- Ad copy character limits and marketing best practices
Documentation Site
User docs live in the sibling repo ../adloop-docs (Mintlify,
docs.getadloop.com — push to main deploys). After any tool or toolset
change here, regenerate the docs tool reference and push it:
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.
- 2d ago First seen · 77 lines · 796 tokens per session scan A cd3fbcc90103
adloop CLAUDE.md is an instructions file published in the GitHub repository kLOsk/adloop (255 stars, last pushed 1mo ago), licensed MIT. It adds 796 tokens to every session, about $0.0040 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 2026-08-30.
Other instructions, from other repositories
marketing-skills AGENTS.md
Instructions for hyperfx-ai/marketing-skills, covering agents.md, what this repo is, available skills, foundation and paid ads.
marketing-skills CLAUDE.md
Instructions for hyperfx-ai/marketing-skills, covering claude.md, what this repo is, available skills, foundation and paid ads.
mureo AGENTS.md
Instructions for logly/mureo, covering agents.md, project overview, build & test, runner — no package.json, no dependencies, no build step and architecture.
mureo CLAUDE.md
Instructions for logly/mureo: When working with this repository, follow all guidelines in AGENTS.md.
google-analytics-mcp AGENTS.md
Instructions for surendranb/google-analytics-mcp, covering agents.md — agent operating manual, ⚡ 1. fast install & client wiring (start here), or launch directly via stdio, client config snippet (mcp.json / claudedesktopconfig.json) and 📖 2. what this repo is.
analytics-mcp CLAUDE.md
Claude Code instructions for karenrebecag/analytics-mcp, covering claude.md — analytics-mcp, non-negotiable rules, conventions (inherited from powerautomatemcp), phase gates and scope.