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 tmj-90/gaffer --skill copywritinggit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/copywriting)<a href="https://agentmods.dev/skills/tmj-90/gaffer/copywriting"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/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/tmj-90/gaffer/copywriting"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/copywriting.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 | $0.00083 | $0.01208 |
| Opus 5.5 | $0.00033 | $0.00483 |
| Sonnet 5.5 | $0.00017 | $0.00242 |
| Haiku 4.5 | $0.00008 | $0.00121 |
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 20d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write marketing copy that converts
Clarity beats cleverness. Good copy meets the reader where their awareness is, speaks in their words, makes specific claims it can prove, and asks for one clear action.
Inputs (collect before writing)
- Page type and the ONE primary action.
- Audience: who they are, the job they are trying to get done, and the words they use for it. Pull those words from reviews, support tickets, interview notes and sales calls (voice-of-customer).
- Awareness level (Eugene Schwartz, Breakthrough Advertising). This decides
where the copy opens:
- Unaware: open on a story or insight about the situation.
- Problem-aware: open on the problem (PAS).
- Solution-aware: open on why this approach beats the others.
- Product-aware: open on the proof and the offer.
- Most aware: open on the offer and the CTA, and not much else.
- Differentiation: why this rather than the obvious alternative, including "do nothing".
- Proof you actually have: numbers, named customers, testimonials, guarantees.
- Traffic source: it sets the awareness level and the message the headline must match.
When running unattended, take these from the ticket, the repo (BRAND.md, existing
pages) and the lore (search_lore). Never invent proof. A missing testimonial or
number becomes a clearly marked [TODO: proof] placeholder and is listed in your
report. It is never a fabricated quote or statistic.
Principles
- Outcome over mechanism. Translate each feature into what the user gets. "256-bit encryption" becomes "Only you can read your files".
- Customer language. If users say "reconciliation is a nightmare", write that, not "streamline financial operations".
- Specific over general. "Save 2 hours a week" beats "save time". "4,200 teams" beats "thousands". Specific claims are believed, and they must be true.
- One idea per section. Each section answers one question a visitor has, in the order they would ask it.
- Plain words. Use short sentences and active voice, and cut filler ("we're passionate about…", "world-class", "seamless").
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.
- 20d ago Changed · +33 lines 7b33762b6830
- 1mo ago First seen · 70 lines · 83 tokens per session scan A 969e794beb55
copywriting is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,208 once invoked, about $0.0003 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
bulwark-brainstorm
Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.
plan-creation
Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.
anthropic-validator
Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.