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 agentmods add skills/jcottam/agent-resources/content-wireframenpx skills add jcottam/agent-resources --skill content-wireframegit clone --depth 1 https://github.com/jcottam/agent-resourcesWrote 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/jcottam/agent-resources/content-wireframe)<a href="https://agentmods.dev/skills/jcottam/agent-resources/content-wireframe"><img src="https://agentmods.dev/badge/skills/jcottam/agent-resources/content-wireframe.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 | $0.00093 | $0.02362 |
| Opus 5 | $0.00046 | $0.01181 |
| Sonnet 5 | $0.00019 | $0.00472 |
| Haiku 4.5 | $0.00009 | $0.00236 |
Grade A, and why
content-wireframe 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 4d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Wireframe
Write every word a page needs — in order, with intent annotations — before touching layout, color, or code. The wireframe is the blueprint; design follows.
When to use
- New website or landing page where copy hasn't been written
- Redesign where the existing page was built design-outward and the words feel secondary
- Any project where the user is unhappy with the "feel" but can't articulate why (often a content problem, not a design problem)
Inputs to gather
Before drafting, collect as much of the following as possible:
- Business context — What does the company do? Who are the customers?
- Primary goal — What is the single most important action a visitor should take?
- Brand voice — Formal/casual? Technical/approachable? Any existing style guide?
- Existing copy — Current site, marketing materials, internal docs
- Competitor pages — Direct competitors' sites, their messaging, positioning, and gaps
- Data files — Locations, pricing, FAQs, testimonials, team bios — anything structured
- Constraints — Pre-launch? Pricing TBD? Missing photography? Legal requirements?
Sources: AGENTS.md, README.md, existing page files, data modules, brand guides, and conversation context.
Audience model
After gathering inputs, define the audience before writing a word. Produce a short profile for each distinct audience segment the page must address:
- Who they are — Role, situation, level of awareness of the problem/product
- What they already believe — Assumptions, prior experiences, mental models
- What objections they carry — Reasons they might leave without acting
- What language they use — How they describe the problem in their own words
Reference the relevant audience segment in each section's intent annotation (e.g., "This section targets first-time visitors who don't yet understand what the product does"). If a section doesn't clearly serve at least one segment, question whether it belongs.
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.
- 4d ago First seen · 257 lines · 93 tokens per session scan A 4b4ff74575d0
content-wireframe is a skill published in the GitHub repository jcottam/agent-resources (30 stars, last pushed 28d ago), licensed MIT. It adds 93 tokens to every session and 2,362 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
pipefy-automations
Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). Covers 16 MCP tools. For AI agents (conversational), see skills/ai-agents/.
summarize-session
Summarize the current session and generate reusable Claude rules, skills, or commands.
new-adapter
Add support for a new AI tool with adapters, CLI, completion, and tests.
update-knowledge-base
Analyze code changes and update KNOWLEDGEBASE.md with architectural and feature changes.
implement
Implement a feature or fix with automatic validation.
python-style
Validate Python code against style and architectural conventions.