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 page-crogit 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/page-cro)<a href="https://agentmods.dev/skills/tmj-90/gaffer/page-cro"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/page-cro.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.00869 |
| Opus 5 | $0.00039 | $0.00434 |
| Sonnet 5 | $0.00015 | $0.00174 |
| Haiku 4.5 | $0.00008 | $0.00087 |
Grade A, and why
page-cro 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 7d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve page conversion rates
A page that converts well is one where the visitor's question ("is this for me?") is answered before they think to ask it. Diagnose in order of impact; fix the biggest lever first.
Analysis framework (work top-to-bottom)
1. Value proposition clarity (highest impact)
Can a first-time visitor understand what this is and why they should care within 5 seconds?
Signs it's broken:
- Headline describes the product, not the outcome for the user.
- Subheadline is a marketing tagline, not a one-sentence expansion of the benefit.
- First CTA is below the fold on desktop (1440px).
2. Headline effectiveness
- Specific > clever. "Cut your Shopify return rate by 23%" beats "Returns, reinvented."
- Must match the ad/email/referral that sent the visitor — message mismatch kills conversions.
- A/B test at ≥ 100 visitors per variant before concluding.
3. CTA friction
- One primary action per page. Two CTAs = zero conversions.
- CTA label states what happens next: "Start free trial" not "Submit".
- Reduce fields: every additional form field costs ~10% completion. Ask for email only until you need more.
4. Social proof specificity
- Named testimonials (first name + company) outperform anonymous quotes.
- Numbers anchor trust: "4,200 teams" > "thousands of teams".
- Logo strips: name-recognisable logos; max 6 (more = noise).
5. Objection handling
Map the 5 core objections for the page's conversion goal (sign-up / purchase / demo). Confirm each is addressed somewhere on the page. See landing-page-generator references for the standard objection list.
6. Mobile and speed
- 60%+ of traffic is mobile for most marketing pages. Check layout at 375px.
- LCP > 2.5s is a conversion killer — check Lighthouse and fix the hero image.
Steps
- Identify page type and primary conversion goal. Single goal per analysis — don't try to optimise for multiple actions simultaneously.
- Run the 5-second test. Read only the above-the-fold content. Can you answer: what is this, who is it for, what happens when I click? If not — fix the hero first, everything else is secondary.
- Work the framework in order. Value prop → headline → CTA → social proof → objections → mobile/speed. Don't skip to lower items until the higher ones are solid.
- Produce prioritised recommendations. For each finding: what's broken, why it hurts, what to change, estimated impact (high/medium/low).
- Verify. After implementing: re-run Lighthouse; confirm primary CTA is above the fold; confirm the 5-second test passes.
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.
- 7d ago First seen · 73 lines · 77 tokens per session scan A a0dd5318c5a4
page-cro is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 77 tokens to every session and 869 once invoked, about $0.0004 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
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.