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 | $0.00039 | $0.03081 |
| Opus 5.5 | $0.00016 | $0.01232 |
| Sonnet 5.5 | $0.00008 | $0.00616 |
| Haiku 4.5 | $0.00004 | $0.00308 |
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 25d 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COPY-ENGINEER v2.0 — Conversion-Oriented Writing (Premium)
Mathematical Compliance: This skill implements the DEPTH-MATHEMATICS specification. It computes and outputs ADS phase activation, CEI components, SI components, cognitive traces (specificity calculus, conversion proof ), and verifies Gates V1, V3, V5. It formalizes conversion copy as a measurable calculus.
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.
New in v2.0: Mathematical depth metrics, specificity calculus, conversion proof , recursive self-audit, verification gates.
The Protocol
0 — PARAMETERIZE: Read Thinking Parameters
Read thinking_parameters:
require_calculus(default true) — compute specificity calculusrequire_proof_(default true) — issue conversion proofrecursion_depth(default 1) — recursive self-audit rounds
1 — SPECIFICITY CALCULUS (if require_calculus = true)
NEW IN v2.0 — Formal calculus for copy specificity.
SPECIFICITY CALCULUS
────────────────────────────────────────
Core Message: [What is the single most important message? ≤10 words]
For each claim in the copy:
Claim: [exact text]
Type: [ADJECTIVE / CLAIM / PROMISE / FEATURE / BENEFIT]
Current: [what the copy currently says]
Specific Version: [evidence/demonstration/proof replacement]
Specificity Score: [0.0-1.0]
1.0 = measurable evidence (numbers, time, count, %)
0.7 = demonstration (steps, process, method)
0.4 = specific example (case study, testimonial)
0.1 = vague adjective/claim
Aggregate Specificity = Σ (Claim_Score × Claim_Importance) / Σ Importance = [0.0-1.0]
Thresholds:
≥ 0.8: HIGH SPECIFICITY — conversion-ready
0.5-0.8: MODERATE — needs work
< 0.5: LOW — rewrite required
Adjective Count: [N — target 0]
Jargon Count: [N — target 0 unless audience uses daily]
Qualifier Count: [N — "very", "really", "actually", "quite" — target 0]
────────────────────────────────────────
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.
- 25d ago Changed · +330 lines · +16 tokens per session 20fce0502572
- 1mo 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 (5 stars, last pushed 13d ago), licensed MIT. It adds 39 tokens to every session and 3,081 once invoked, about $0.0002 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 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…
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
rational-buddhism
A way to examine spiritual, supernatural, or other difficult-to-test claims using skepticism, personal testing, and scientific standards.