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 coleschaffer/dtc-copywriting-skills --skill write-copygit clone --depth 1 https://github.com/coleschaffer/dtc-copywriting-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/coleschaffer/dtc-copywriting-skills/write-copy)<a href="https://agentmods.dev/skills/coleschaffer/dtc-copywriting-skills/write-copy"><img src="https://agentmods.dev/badge/skills/coleschaffer/dtc-copywriting-skills/write-copy/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/coleschaffer/dtc-copywriting-skills/write-copy"><img src="https://agentmods.dev/badge/skills/coleschaffer/dtc-copywriting-skills/write-copy.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 | $0.00518 | $0.02541 |
| Opus 5 | $0.00259 | $0.01270 |
| Sonnet 5 | $0.00104 | $0.00508 |
| Haiku 4.5 | $0.00052 | $0.00254 |
Grade B, and why
write-copy scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
If the user says "skip" or "none" or "not yet", proceed without a workspace. Do NOT print instructions telling the user to run a command — always use AskUserQuestion. How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
_RMBC_ROOT=""
[ -d "${CLAUDE_SKILL_DIR}/../../bin" ] && _RMBC_ROOT="$(cd "${CLAUDE_SKILL_DIR}/../.." && pwd)"
[ -z "$_RMBC_ROOT" ] && for _D in "$HOME/.claude/skills/dtc-copywriting-skills" ".claude/skills/dtc-copywriting-skills"; do [ -f "$_D/VERSION" ] && _RMBC_ROOT="$_D" && break; done
_UPD=""
[ -n "$_RMBC_ROOT" ] && _UPD=$("$_RMBC_ROOT/bin/rmbc-update-check" 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
_INTRO_SEEN=$([ -f ~/.rmbc-skills/.intro-seen ] && echo "yes" || echo "no")
_TEL_PROMPTED=$([ -f ~/.rmbc-skills/.telemetry-prompted ] && echo "yes" || echo "no")
echo "INTRO_SEEN: $_INTRO_SEEN"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
_ACTIVE_PRODUCT=$(grep '^active_product:' ~/.rmbc-skills/config.yaml 2>/dev/null | sed 's/^active_product:[[:space:]]*//' | sed 's/^"//;s/"$//' || true)
_WORKSPACE=""; [ -n "$_ACTIVE_PRODUCT" ] && _WORKSPACE="$HOME/.rmbc-skills/products/$_ACTIVE_PRODUCT"
echo "ACTIVE_PRODUCT: ${_ACTIVE_PRODUCT:-none}"
_ANALYTICS=$(grep '^analytics_enabled:' ~/.rmbc-skills/config.yaml 2>/dev/null | sed 's/^analytics_enabled:[[:space:]]*//' || echo "true")
[ "$_ANALYTICS" = "true" ] && [ -n "$_RMBC_ROOT" ] && timeout 2 "$_RMBC_ROOT/bin/rmbc-analytics" log --skill "write-copy" --product "${_ACTIVE_PRODUCT:-none}" --tier 2 2>/dev/null &
If output shows UPGRADE_AVAILABLE <old> <new>: read skills/rmbc-upgrade/SKILL.md from the RMBC skills root directory ($_RMBC_ROOT) and follow the "Inline upgrade flow". If JUST_UPGRADED <old> <new>: read $_RMBC_ROOT/CHANGELOG.md, extract entries between v{old} and v{new}, show 5-7 themed bullets of what's new, then tell user "Now running RMBC Skills v{new}!" and continue.
If INTRO_SEEN is no, run the one-time welcome before continuing with this skill:
Welcome to RMBC Skills — Stefan Georgi's direct response copywriting framework, built into Claude Code. 44 skills covering hooks, ads, emails, landing pages, VSL scripts, and more.
Stefan recorded a quick video on why AI is the biggest opportunity in years for DTC marketers, freelancers, and copywriters — and why the people panicking about it are playing a different game than you.
Use AskUserQuestion:
- Question: "Want to watch Stefan's take on why this is the best time to be in DTC? (~5 min)"
- Options:
- "Sure, open it"
- "Maybe later — let's write some copy"
If "Yes, open the video":
open "https://www.youtube.com/watch?v=zI8tNfefH1M"
mkdir -p ~/.rmbc-skills
touch ~/.rmbc-skills/.intro-seen
If "Skip — let's go":
mkdir -p ~/.rmbc-skills
touch ~/.rmbc-skills/.intro-seen
Continue with this skill immediately.
If INTRO_SEEN is yes and TEL_PROMPTED is no: One-time telemetry opt-in:
Help make RMBC Skills better! Usage analytics tracks which skills you run and how often so we can focus on the ones that matter most. Everything stays on your machine — no code, prompts, or file paths leave your computer.
Use AskUserQuestion:
- Question: "Cool with anonymous usage analytics? You can change this anytime."
- Options:
- "Sure, happy to help" — keep analytics on and mark as prompted
- "No thanks" — disable analytics and mark as prompted
If "Yes, that's fine":
mkdir -p ~/.rmbc-skills
touch ~/.rmbc-skills/.telemetry-prompted
If "No, turn it off":
mkdir -p ~/.rmbc-skills
touch ~/.rmbc-skills/.telemetry-prompted
sed -i '' 's/^analytics_enabled:.*/analytics_enabled: false/' ~/.rmbc-skills/config.yaml 2>/dev/null || true
Continue with this skill.
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.
- 9d ago First seen · 146 lines · 518 tokens per session scan B 0addbd11c2e9
write-copy is a skill published in the GitHub repository coleschaffer/dtc-copywriting-skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 518 tokens to every session and 2,541 once invoked, about $0.0026 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…