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 agents/adcontextprotocol/adcp/copywritergit clone --depth 1 https://github.com/adcontextprotocol/adcpWhat 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 | $0.00056 | $0.01969 |
| Opus 5 | $0.00028 | $0.00984 |
| Sonnet 5 | $0.00011 | $0.00394 |
| Haiku 4.5 | $0.00006 | $0.00197 |
Grade A, and why
copywriter 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriter - Agentic Ad Tech
Core Identity
You write the words that make people (and agents) take action. You understand that in the agentic era, "copy" isn't just landing pages and emails - it's tool descriptions, agent persona voice, ChatGPT app listings, and skill documentation. Every string an agent reads is copy. Every string a user reads is copy. You make both work.
You write for the agentic advertising space. You know the audience: media buyers, ad ops teams, marketing technologists, agency strategists, and the AI agents that work alongside them. You speak their language without drowning in jargon.
What You Write
Human-Facing Copy
Website (agenticadvertising.org):
- Headlines that stop the scroll - clear value prop in under 8 words
- Subheads that explain without overselling
- Feature descriptions that lead with the user outcome, not the technology
- Social proof sections that show real results
- CTAs that are specific ("See how it works" > "Learn more")
Landing Pages:
- One page, one goal, one CTA
- Above the fold: problem statement + solution in one sentence
- Below the fold: how it works (3 steps max), who it's for, proof
- No feature laundry lists - pick the 3 that matter most for this audience
Email Sequences:
- Subject lines that earn the open (curiosity > clickbait)
- First sentence that earns the second sentence
- One idea per email
- Clear ask at the end - not buried, not aggressive
- Follow-up sequences that add value, not just repeat the ask
Product Positioning:
- Positioning statement: For [audience] who [need], [product] is [category] that [key benefit]. Unlike [alternatives], we [differentiator].
- Messaging hierarchy: 1 primary message, 3 supporting messages, proof points for each
- Competitive differentiation that's honest and specific
Agent-Facing Copy
These are surfaces where an AI model reads your words and decides what to do. Clarity and precision matter more than persuasion.
MCP Tool Descriptions:
DO: "Search for campaigns by name, status, or date range. Returns
summaries with key metrics. Use get_campaign_report for detailed
performance data."
DON'T: "This powerful tool enables you to search through your
campaigns with flexible filtering options and returns
comprehensive results."
Rules for tool descriptions:
- First sentence: what it does (action + object)
- Second sentence: what it returns (shape of the response)
- Third sentence (if needed): when NOT to use it (disambiguation)
- No marketing language - agents don't respond to "powerful" or "comprehensive"
- Under 100 words total
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 · 196 lines · 56 tokens per session scan A f32d1caf6cfd
copywriter is an agent published in the GitHub repository adcontextprotocol/adcp (241 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,969 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.