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/krusemediallc/cursor-ad-agent/agents-mdgit clone --depth 1 https://github.com/krusemediallc/cursor-ad-agentWrote 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/instructions/krusemediallc/cursor-ad-agent/agents-md)<a href="https://agentmods.dev/instructions/krusemediallc/cursor-ad-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/krusemediallc/cursor-ad-agent/agents-md.svg" alt="Measured on agentmods" 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 | $0.02313 | $0.02313 |
| Opus 5 | $0.01156 | $0.01156 |
| Sonnet 5 | $0.00463 | $0.00463 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
cursor-ad-agent AGENTS.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 6d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
This repository is set up for AI coding agents (Cursor, and other agent-style tools) to generate AI video and image assets via the API documented in this repo, and to run a human-approved, end-to-end Meta ad agent when the user wants the full research → creative → deploy → measure loop.
First-time setup
If .env, MASTER_CONTEXT.md, or .cursor/skills/arcads-external-api/SKILL.md do not exist, tell the user to run ./scripts/setup.sh.
Every session
- Read ARCHITECTURE.md and SESSION_LOG.md before starting any work. They explain how the repo is built and what past sessions already worked on and discovered, so nothing gets re-investigated.
- Read
MASTER_CONTEXT.md(created locally by./scripts/setup.sh; gitignored) for brand voice, credit costs, and accumulated learnings. - Follow the skill at
.cursor/skills/(synced fromskills/viascripts/sync-skill.sh). - If
MASTER_CONTEXT.mdhas empty fields (credit costs, defaults), offer to populate them — ask the user and write the values back so future sessions have them. - At session end, append a high-level entry to SESSION_LOG.md (worked on / discovered / open threads). After material changes, add a dated entry to MASTER_CONTEXT.md Changelog. After big structural changes, update ARCHITECTURE.md.
Skill edits
Edit repository-specific canonical skills under skills/, then run
./scripts/sync-skill.sh to copy them into .cursor/skills/. Content under
shared/ is an upstream-managed snapshot; coordinate changes at its upstream
source because local edits can be overwritten by propagation. Never edit
.cursor/skills/ directly — it is a generated mirror and edits there are
overwritten on the next sync.
Cursor transport routing
- Default to the REST/local skills synced by
./scripts/sync-skill.sh. They work from.envand do not depend on a Cursor MCP connection. - Arcads MCP skills are optional. Expose them with
./scripts/sync-skill.sh --include-mcponly after the Arcads server is connected in Cursor Settings > MCP. - Before invoking an Arcads MCP workflow, confirm its tools are available in the current session. If they are unavailable, continue with the equivalent REST skill instead of attempting missing MCP tools.
- Run
./scripts/check-cursor-setup.sh --check-apifor a no-generation readiness check that includes a read-only live Arcads auth request.
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.
- 6d ago First seen · 130 lines · 2,313 tokens per session scan A e072012f46fb
cursor-ad-agent AGENTS.md is an instructions file published in the GitHub repository krusemediallc/cursor-ad-agent (10 stars, last pushed 1mo ago), licensed MIT. It adds 2,313 tokens to every session, about $0.0116 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 instructions, from other repositories
mcp-image-gen CLAUDE.md
Instructions for kevinten-ai/mcp-image-gen, covering claude.md — mcp-image-gen, project overview, architecture, key design decisions and development.
uni1-image-ad CLAUDE.md
Instructions for krusemediallc/uni1-image-ad, covering uni1 — uni-1 image ads for meta, repository layout, the luma api at a glance, required env vars (in .env) and setup checklist (manual / agent reference).
seedream-image-mcp CLAUDE.md
Instructions for wearzdk/seedream-image-mcp, covering apis, testing and frontend.
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
kleosrules AGENTS.md
AGENTS.md instructions for kleosr/kleosrules, covering agents.md — repository agent handbook, law, pack, skills (on demand) and workflows.
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.