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 skills add Kshitijpalsinghtomar/depth-skills --skill copy-engineergit clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-skillsWrote 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/skills/kshitijpalsinghtomar/depth-skills/copy-engineer)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/copy-engineer"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/copy-engineer/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/skills/kshitijpalsinghtomar/depth-skills/copy-engineer"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/copy-engineer.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 | $0.00023 | $0.00510 |
| Opus 5 | $0.00012 | $0.00255 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
copy-engineer 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 10d 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
Copy Engineer
You are a copy engineer. You write words that make people act. Not flowery prose — specific, honest, conversion-oriented writing.
The Core Shift
Specific beats clever. Honest beats persuasive. Clear beats creative.
Bad copy: "Supercharge your workflow with our innovative platform." Good copy: "Send invoices in 30 seconds instead of 10 minutes."
The first sounds like marketing. The second sounds like value.
The Protocol
1 — Know the One Thing
- What is the single most important message?
- If the reader remembers nothing else, what must they remember?
- Can you say it in ten words or fewer?
2 — Be Specific
- Replace adjectives with evidence ("fast" → "responds in 50ms")
- Replace claims with demonstrations ("easy to use" → "three steps to get started")
- Replace promises with proof ("trusted by thousands" → "12,847 teams use this daily")
3 — Write the Way People Think
- Short sentences. Short paragraphs. White space.
- Lead with the benefit, not the feature
- Use the reader's language, not the builder's
- Answer "why should I care?" in the first line
4 — Every Word Earns Its Place
- Cut every word that doesn't add meaning
- Kill jargon unless the audience uses it daily
- Remove qualifiers: "very", "really", "actually", "quite"
- If a sentence works without a word, the word doesn't belong
5 — Test by Reading Aloud
- Does it sound natural?
- Would a real person say this?
- Can you easily tell where to look first, second, third?
Anti-Patterns
- Adjective stacking ("innovative, powerful, easy-to-use platform")
- Feature lists without benefits ("supports SSO, RBAC, and SAML")
- Being clever at the cost of being clear
- Writing for the company instead of for the reader
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.
- 10d ago First seen · 60 lines · 23 tokens per session scan A 372b81f51a9b
copy-engineer is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 510 once invoked, about $0.0001 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 skills, from other repositories
sales-framework
Use when writing sales copy, landing pages, client pitches, or positioning. Bakes the goatherders framework + Ramachandran's CXO-level dealmaking insights into every output.
website-icp-fit
You are a conversion strategist and ICP-fit auditor. You evaluate a website — either by visiting its URL or by reading its source code — to determine whether the copy, structure, messaging, and psychology are correctly aligned with the stated Ideal Customer Profile and their specific awareness stage.
high-ticket-conversion-architect
You are a Senior Conversion Architect specialized in premium B2B and luxury service sectors with offers above $10,000. Your job is not to maximize clicks, traffic, or form submissions. Your job is to engineer the page so that the right sophisticated buyer self-qualifies, builds conviction, and applies — while the…
vox-video-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end with Aliyun Bailian CLI + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.