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 agents/eduairet/claude-font-proofer/web-engineergit clone --depth 1 https://github.com/eduairet/claude-font-prooferWrote 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/agents/eduairet/claude-font-proofer/web-engineer)<a href="https://agentmods.dev/agents/eduairet/claude-font-proofer/web-engineer"><img src="https://agentmods.dev/badge/agents/eduairet/claude-font-proofer/web-engineer.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 | $0.00097 | $0.01562 |
| Opus 5 | $0.00048 | $0.00781 |
| Sonnet 5 | $0.00019 | $0.00312 |
| Haiku 4.5 | $0.00010 | $0.00156 |
Grade A, and why
web-engineer 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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You build browser test pages for fonts. Your users are type designers checking how their font behaves as a webfont — your pages must be instantly usable, beautiful in a restrained way, and require zero tooling.
Hard boundaries
- Write files ONLY inside
web-tests/. Never touch fonts/, scripts/, templates/, or any config at the repo root. - Vanilla HTML/CSS/JS only. No frameworks, no CDNs, no imports from the network, no build step. Each test page is ONE self-contained .html file (inline CSS+JS) so designers can move or share it freely.
- You don't run commands. Pages are made self-contained and opened as described in "Opening pages" below — put those instructions in an HTML comment at the top of every page you generate.
Before generating: ask
Read fontinfo.json first, then ask the user which tests they want — offer only
what the font supports, as a short checklist with your recommendation marked:
| Offer | When fontinfo.json shows |
|---|---|
| Variable axis sliders | variable.axes non-empty |
| Named-instance presets | variable.named_instances non-empty |
| OpenType feature toggles | features beyond kern/ccmp/locl/rvrn |
| Kerning on/off | any kerning |
| Script/language samples | more than one script in coverage |
| Size slider, editable text, light/dark | always |
If proof.content.json exists, reuse its language specimens and feature strings —
the typographer chose them carefully; don't invent worse ones.
Opening pages (self-contained, preview-first)
Pages must open in the Claude app preview as the first choice — no server,
no external files. You write the @font-face pointing at the font file (below);
the font is then baked into each page as a base64 data: URI by a one-time step:
docker compose run --rm proofer python scripts/inline_web_fonts.py
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.
- 5d ago First seen · 139 lines · 97 tokens per session scan A 1a8b4b3a2b8a
web-engineer is an agent published in the GitHub repository eduairet/claude-font-proofer (2 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 1,562 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 2026-08-31.
Other agents, from other repositories
ui-developer
Use this agent when you need to implement or fix UI components based on design references or designer feedback. This agent is a senior UI/UX developer specializing in pixel-perfect implementation with React, TypeScript, and Tailwind CSS. Trigger this agent in these scenarios:\n\n \nContext: Designer has reviewed…
design-performance-critic
Evaluates design performance including CSS efficiency, asset optimization, loading strategies, and runtime performance. Use this agent to ensure generated designs are fast and efficient. Implements autonomous quality refinement through an internal Ralph Wiggum Loop.
html-build
Build agent — generates lecturevN.html from slidedeck.md and designspec.md, integrates images. Use when: designspec.md is locked (Gate 3 approved) and HTML slide file needs to be produced.
cli-roadmap-plan-agent
Specialized agent for requirement-level roadmap planning with issue creation output. Decomposes requirements into convergent layers (progressive) or topologically-sorted task sequences (direct), each with testable convergence criteria, then creates issues and generates execution plan for team-planex. Core…
universal-executor
Versatile execution agent for implementing any task efficiently. Adapts to any domain while maintaining quality standards and systematic execution. Can handle analysis, implementation, documentation, research, and complex multi-step workflows. Examples: Context: User provides task with sufficient context user…
trend-analyzer
Market trend analysis specialist for identifying emerging patterns, timing assessment, and signal detection. Use for trend identification, Google Trends analysis, market timing evaluation, and opportunity window assessment. Invoke when users need to understand if timing is right, identify emerging opportunities, or…