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 Rylaispirit/rylai-codex-hermes-skills --skill copywritinggit clone --depth 1 https://github.com/Rylaispirit/rylai-codex-hermes-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/rylaispirit/rylai-codex-hermes-skills/copywriting)<a href="https://agentmods.dev/skills/rylaispirit/rylai-codex-hermes-skills/copywriting"><img src="https://agentmods.dev/badge/skills/rylaispirit/rylai-codex-hermes-skills/copywriting/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/rylaispirit/rylai-codex-hermes-skills/copywriting"><img src="https://agentmods.dev/badge/skills/rylaispirit/rylai-codex-hermes-skills/copywriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 113 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00036 | $0.00933 |
| Opus 5.5 | $0.00014 | $0.00373 |
| Sonnet 5.5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
copywriting 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriting
Create persuasive copy without inventing claims, customers, urgency, or results. The goal is to help the intended reader understand the offer, trust the evidence, and take one appropriate next action.
Runtime Compatibility
- Resolve every bundled file relative to this skill directory.
- In Codex, use the available workspace, browser, and research tools.
- In Hermes, map those steps to equivalent tools exposed by the runtime.
- Check tool access before promising research, file edits, publishing, or tests.
Intake
Collect what is already available before asking questions:
- offer, product, or service;
- target audience and buying context;
- desired action;
- channel and format;
- voice, language, and length;
- verified proof, constraints, and prohibited claims.
Ask only for missing details that would materially change the copy. If the user wants a fast draft, state the assumptions briefly and continue.
Workflow
-
Define the job
- Write one sentence describing the audience, problem, desired outcome, and next action.
- Separate the primary promise from supporting benefits.
-
Build an evidence inventory
- List available product facts, demonstrations, customer language, metrics, guarantees, and limitations.
- Mark unsupported claims as gaps. Do not turn gaps into marketing facts.
-
Choose a message path
- Problem-led: useful when the audience already recognizes the pain.
- Outcome-led: useful when the benefit is concrete and easy to picture.
- Mechanism-led: useful when the method is the meaningful differentiator.
- Proof-led: useful when credible evidence is the strongest reason to care.
-
Draft for the channel
- Lead with the clearest relevant value.
- Keep one primary call to action.
- Put proof close to the claim it supports.
- Use headings and short blocks for scan-heavy surfaces.
- Match commitment level to audience intent.
-
Review
- Remove vague superlatives and unnecessary pressure.
- Confirm every number, quote, deadline, comparison, and customer reference.
- Check that the headline, body, and CTA promise the same outcome.
- Produce variants only when each tests a distinct hypothesis.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 135 lines · 36 tokens per session scan A 30239501a81c
copywriting is a skill published in the GitHub repository Rylaispirit/rylai-codex-hermes-skills (63 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 933 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
atomicmail
Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.
hermesoffice-decks
Produce presentations in HermesOffice Slides — the plandeck/generatedeck pipeline, native element editing, and the templates/decks style specs (modern, elegant, professional, keynote-speaker, minimal, tech-dark, investor-pitch, workshop). Load for any request that creates or restyles a deck.
skill-maintainer
Use when tracking upstream drift and syncing adapted skill libraries.
notebooklm-mode
Source-grounded research pipeline inspired by NotebookLM. Collect verbatim source extracts into a temporary workspace, then answer questions and create deliverables grounded in those sources. Two grounding modes: strict (vault-only) and augmented (vault + labeled [background] knowledge). Trigger when the user asks to…
travel-itinerary
Use when the user needs a business-trip itinerary built, updated, shared, or exported — create, update, sanitize, route, and export structured business-trip itineraries from booking confirmations, emails, tickets, PDFs, screenshots, calendar invites, or notes. Covers day-by-day itinerary generation, privacy-safe…
scheduled-summary
Use when a recurring cross-session digest should be produced and delivered via Hermes cron — aggregates session activity, cron job outputs, memory changes, and tool usage stats into a compact summary for delivery via messaging platforms. Surfaces outstanding tasks and cross-session context that's invisible on chat…