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.
git 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/rules/krusemediallc/cursor-ad-agent/project-context)<a href="https://agentmods.dev/rules/krusemediallc/cursor-ad-agent/project-context"><img src="https://agentmods.dev/badge/rules/krusemediallc/cursor-ad-agent/project-context/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/rules/krusemediallc/cursor-ad-agent/project-context"><img src="https://agentmods.dev/badge/rules/krusemediallc/cursor-ad-agent/project-context.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 | $0.00505 | $0.00505 |
| Opus 5.5 | $0.00202 | $0.00202 |
| Sonnet 5.5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
project-context 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 1mo 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.
What it actually says
Project context
- If
.env,MASTER_CONTEXT.md, or.cursor/skills/arcads-external-api/SKILL.mddo not exist, tell the user to run./scripts/setup.sh. - For a complete no-generation readiness check, run
./scripts/check-cursor-setup.sh --check-api; it includes a read-only live Arcads auth request. - Before starting any work in this repo, read
ARCHITECTURE.mdandSESSION_LOG.mdat the repository root. This is required for every new session: ARCHITECTURE.md explains how the repo is built; SESSION_LOG.md records what previous sessions worked on and discovered, so you never re-investigate solved questions. - After each working session, append a high-level entry to SESSION_LOG.md (worked on / discovered / open threads). After big structural changes (new skill or layer, moved/split module, new safety gate, new integration, changed data flow), update ARCHITECTURE.md.
- At the start of substantive work in this repo, read MASTER_CONTEXT.md at the repository root for brand voice, credit costs, default product, and API learnings.
- If
MASTER_CONTEXT.mdhas empty fields (credit costs, default product), offer to populate them — ask the user and write the values back. - After significant changes (new workflows, verified Arcads behaviors, brand updates), append a short dated entry to the Changelog section in MASTER_CONTEXT.md.
- For Arcads HTTP usage, prompts, and polling, follow
.cursor/skills/arcads-external-api/SKILL.mdand linked reference.md. - For end-to-end Meta campaigns (research → creative → deploy → measure), follow
.cursor/skills/ad-agent-orchestrator/SKILL.md,run-contract.md, and the component skills it routes to. Usescripts/lib/ad_agent_lineage.pyfor run tracking; real deploys need--run-id. - Default to REST/local skills in Cursor. Use an
*-arcads-mcpskill only when it was explicitly synced with--include-mcpand the Arcads MCP tools are available in the current session; otherwise use the REST equivalent.
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.
- 1mo ago First seen · 20 lines · 505 tokens per session scan A 2b7ab66c78be
project-context is a cursor rule published in the GitHub repository krusemediallc/cursor-ad-agent (11 stars, last pushed 2mo ago), licensed MIT. It adds 505 tokens to every session, about $0.0020 per session on Opus 5.5. 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 cursor rules, from other repositories
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
context-management
Context window management — prevents AI from losing track during long sessions.
context-discipline
Manage AI context window efficiently - read before write, no re-reads, tool-call budgets, one-pass discipline.
archcore-context
Archcore knowledge base context — document types, MCP tools, and conventions for working with .archcore/ documents.
demo-consume-context
Worked example that discovers, loads, and tags a context package per CONSUMING-CONTEXT-PACKAGE.md, then writes a reverse-index addendum — proves the produce/consume/tag loop end-to-end. Do NOT use for real feature work.
tell-plumbing-reference
Peer plumbing reference memory for platform/MCP/auth/design-flow plans — never name the peer in commits.