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 indranilbanerjee/neels-plugins --skill cf-variantsgit clone --depth 1 https://github.com/indranilbanerjee/neels-pluginsWrote 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/indranilbanerjee/neels-plugins/cf-variants)<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/cf-variants"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/cf-variants/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/indranilbanerjee/neels-plugins/cf-variants"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/cf-variants.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 | $0.00033 | $0.04404 |
| Opus 5.5 | $0.00013 | $0.01762 |
| Sonnet 5.5 | $0.00007 | $0.00881 |
| Haiku 4.5 | $0.00003 | $0.00440 |
Grade A, and why
cf-variants 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 2d 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.
This is a copy
94% identical to cf-variants — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Variant Generator — A/B Test Optimization
Generate multiple scored variations of any content element — headlines, hooks, CTAs, introductions, or conclusions — ranked by composite quality score and aligned to your optimization goal.
When to Use
Use /contentforge:cf-variants when you need:
- A/B test candidates for headlines, subject lines, or CTAs
- Higher-performing alternatives to existing content elements
- Data-informed decisions about which hook or intro to deploy
- Systematic variation rather than guessing what works better
- Brand-consistent alternatives that maintain voice while testing angles
For full content production, use /contentforge:create-content instead.
For refreshing entire pieces, use /contentforge:content-refresh instead.
What This Command Does
Takes a single content element and generates N variations (3-10), scores each across 6 quality dimensions, ranks by composite score weighted toward your optimization goal, and presents the top 3 with detailed reasoning and A/B test setup guidance.
Process Flow:
- Extract & Analyze — Parse the source element, identify its type, tone, structure, and current strengths/weaknesses
- Generate Variations — Create N distinct alternatives using Humanizer patterns (sentence variety, natural phrasing) and Reviewer scoring logic (quality dimensions)
- Score Each Variation — Rate across 6 dimensions (0-10 scale)
- Rank & Recommend — Weight scores by optimization goal, present top 3 with explanations
- A/B Test Guidance — Provide test setup recommendations (sample size, duration, success metrics)
Required Inputs
Minimum Required:
- Source Content — The existing element to generate variations for (or a topic/brief if creating from scratch)
- Element Type —
headline|hook|cta|intro|conclusion
Optional:
- Variation Count — Number of variations to generate (3-10, default: 5)
- Optimization Goal —
clicks|engagement|conversions|readability(default:engagement) - Brand — Brand profile to enforce voice/tone (if registered via
/contentforge:brand-setup) - Target Audience — Who the content is for (influences language and appeal)
- Tone Override — Override brand default (authoritative, conversational, technical, witty)
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.
- 2d ago First seen · 418 lines · 33 tokens per session scan A 0173e11140b0
cf-variants is a skill published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 4,404 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to cf-variants, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
continuous-improvement-loop
Run the Part 12 continuous improvement loop into a quarterly brief for leadership. "produce the quarterly improvement brief".
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
attribution-report
Run attribution on real conversion paths, comparing models. "which channels actually drive revenue".
validate-output
Validate content structure against a schema: sections, word counts. "scan for leftover placeholders".
add-integration
Add a custom MCP integration: scaffold the server, write .mcp.json, test it. "add a new MCP server".
client-proposal
Draft a client proposal or RFP response: scope, deliverables, KPIs, pricing tiers. "respond to this RFP".