project-context

project-context is a cursor rule for Cursor from krusemediallc/cursor-ad-agent. It costs 505 tokens per session, scanned A, original, MIT.

A project-memory rule set built around files such as ARCHITECTURE.md, SESSION_LOG.md, and MASTER_CONTEXT.md.

In plain words
What is it for?
Loading repository context before work and recording discoveries or major structural changes afterward.
Why use it?
It helps an agent understand how a repository works and remember earlier findings instead of repeating investigations.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/krusemediallc/cursor-ad-agent/project-context
Clone the repo
git clone --depth 1 https://github.com/krusemediallc/cursor-ad-agent

Made for: Cursor.

Per session 505 This file is loaded in full into every session.
When invoked 505 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00505 $0.00505
Opus 5 $0.00253 $0.00253
Sonnet 5 $0.00101 $0.00101
Haiku 4.5 $0.00051 $0.00051

Measured 3d ago against content hash 2b7ab66c78be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

.cursor/rules/project-context.mdc · 20 lines

What it actually says

Project context

  • If .env, MASTER_CONTEXT.md, or .cursor/skills/arcads-external-api/SKILL.md do 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.md and SESSION_LOG.md at 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.md has 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.md and 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. Use scripts/lib/ad_agent_lineage.py for run tracking; real deploys need --run-id.
  • Default to REST/local skills in Cursor. Use an *-arcads-mcp skill only when it was explicitly synced with --include-mcp and the Arcads MCP tools are available in the current session; otherwise use the REST equivalent.
Changes

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.

  1. 3d ago First seen · 20 lines · 505 tokens per session scan A 2b7ab66c78be

Subscribe to this mod's changes

project-context is a cursor rule published in the GitHub repository krusemediallc/cursor-ad-agent (10 stars, last pushed 1mo ago), licensed MIT. It adds 505 tokens to every session, about $0.0025 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.