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/amekala/ads-mcpWrote 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/amekala/ads-mcp/brand-workspace)<a href="https://agentmods.dev/rules/amekala/ads-mcp/brand-workspace"><img src="https://agentmods.dev/badge/rules/amekala/ads-mcp/brand-workspace.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 | $0.00431 | $0.00431 |
| Opus 5 | $0.00216 | $0.00216 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
brand-workspace 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 7d 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
Brand Workspace Context
When working on advertising, campaign, or marketing tasks in this project:
-
Check for BRAND.md in the project root. If it exists, read it before answering any advertising question. It contains brand voice, audiences, KPI targets, budget guardrails, and platform status.
-
Check for memory at
.cursor/memory/performance-marketing-agent/MEMORY.md. If it exists, read it for past decisions, learnings, and user preferences. -
If BRAND.md does not exist, this is a new brand workspace. Use the
adspirer-setupskill to bootstrap it — scan local docs, pull live data from Adspirer MCP, and generate BRAND.md. -
Brand docs in the project folder (
.md,.txt,.csv,.yaml,.json,.pdf) contain brand guidelines, media plans, and strategy notes. Read relevant files when writing ad copy, creating campaigns, or making recommendations. -
Always use live data from the Adspirer MCP server alongside brand context. Never answer performance questions from memory alone — pull fresh data.
-
Update BRAND.md when significant changes happen (new platforms connected, new brand docs added, major strategy shifts). Update MEMORY.md after every campaign action with what was done and why.
-
Strategy directives are binding context. If
STRATEGY.mdexists, all campaign creation, keyword management, and ad copy tasks MUST read it first. AVOID directives deprioritize matching keywords. CONSTRAINT directives are binding rules. After strategy work, propose new directives for user confirmation and persist confirmed ones to STRATEGY.md. -
Known platform constraints must be surfaced proactively. For Google Ads workflows, remind users that conversion action primary/secondary configuration is manual in Google Ads UI (not currently configurable via Adspirer MCP tools).
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.
- 7d ago First seen · 25 lines · 431 tokens per session scan A 22d06b165a26
brand-workspace is a cursor rule published in the GitHub repository amekala/ads-mcp (88 stars, last pushed 22d ago), licensed MIT. It adds 431 tokens to every session, about $0.0022 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 cursor rules, from other repositories
agent-severance
Offboard an AI agent the way you'd offboard an employee — inventory what it knew and touched, export then purge its memory, revoke every credential and access grant, and write the handover for its successor (human or agent). Use when decommissioning an agent or bot, switching agent vendors, ending an AI pilot, or when…
context-bankruptcy
Declare bankruptcy on a long-lived AI agent's accumulated memory — audit what it currently believes, separate ground truth from stale and wrong, purge deliberately, restate the truths that survive, and log what was lost. Use when an agent keeps acting on outdated facts, contradicts itself across sessions, 'remembers'…
context-engineering-review
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut token usage without losing quality, debug an agent that ignores instructions, or audit how retrieval results, history, and…
memory-file-maintenance
Keep your AI memory/context file (MEMORY.md, CLAUDE.md, custom instructions) healthy over time — pruning the stale, adding the new, and keeping it sharp so your AI keeps getting you right. Use when asked review my memory file, my AI context is outdated, clean up my CLAUDE.md, or maintain my AI instructions. Produces a…
memory-five-layers
Sistema de memória persistente entre sessões — carregamento de contexto + salvamento explícito + watcher automático.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.