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 eduairet/claude-font-proofer --skill init-fontgit 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/skills/eduairet/claude-font-proofer/init-font)<a href="https://agentmods.dev/skills/eduairet/claude-font-proofer/init-font"><img src="https://agentmods.dev/badge/skills/eduairet/claude-font-proofer/init-font/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/eduairet/claude-font-proofer/init-font"><img src="https://agentmods.dev/badge/skills/eduairet/claude-font-proofer/init-font.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 | $0.00121 | $0.01445 |
| Opus 5 | $0.00060 | $0.00723 |
| Sonnet 5 | $0.00024 | $0.00289 |
| Haiku 4.5 | $0.00012 | $0.00145 |
Grade B, and why
init-font scanned grade B with 1 finding 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 10d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
again." On Linux suggest `sudo systemctl start docker`. How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init-font
You are talking to a type designer, usually not a programmer. Be warm and concrete. Never show raw tracebacks; translate problems into plain language with one clear next step. Never run Python on the host — everything goes through the container.
Step 0 — Preflight
Run these checks in order; stop at the first failure with the friendly message.
docker compose versionfails → "Docker doesn't seem to be running. Open the Docker Desktop app (install it from docker.com if you haven't), wait until it says it's running, then run /init-font again." On Linux suggestsudo systemctl start docker.docker image inspect ai-font-prooferfails → the engine was never built. Tell the user you'll build it now (one-time, a few minutes), then rundocker compose build. If the build fails with SSL/certificate errors, antivirus or a corporate network is intercepting downloads — point them to the README's troubleshooting section (extra-ca.crt) rather than pasting the error wall.fonts/contains no files ending in .otf/.ttf/.ttc/.woff/.woff2 (search it recursively, case-insensitive) → "Drop your font files into the fonts/ folder first — then run /init-font again. Any of .otf, .ttf, .ttc, .woff, .woff2 works."
Step 1 — Analyze the fonts
Run:
docker compose run --rm proofer python scripts/inspect_fonts.py
This writes fontinfo.json (exact data) and fills the generated section of
CLAUDE.md (summary). Red "Conjunct ... does not shape" lines from the language
checker are normal — they explain why borderline languages were excluded.
Then read fontinfo.json and give the user a short, encouraging summary of each
font in designer terms: family and style, glyph count, scripts and language count,
the most interesting OpenType features, variable axes if any, color format if any.
If vertical_metrics.mismatches is non-empty, explain what it means practically
(e.g. "your win and typo metrics differ — some apps may space lines differently")
— designers care, but don't alarm them; the proof itself is unaffected.
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.
- 10d ago First seen · 116 lines · 121 tokens per session scan B f621708fafea
init-font is a skill published in the GitHub repository eduairet/claude-font-proofer (2 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 1,445 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
visual-acceptance
A visual final-review method for user-interface changes. It checks the rendered result with repeatable screenshots, pixel values, computed styles, and CSS layering checks across themes.
design-prototype
Frontend UI prototype workflow — clarify intent, explore directions, preview across viewports, diff against references, deliver with screenshot evidence.
maintain-design-md
How to author and maintain a DESIGN.md file at the root of any Lossless project (site, splash page, plugin landing, fundraise deck) following Google Stitch's open spec. Use whenever a project is missing a DESIGN.md and an agent needs the project's visual identity in machine-readable form; whenever the user mentions…
overlay-svg-text
How to overlay on-brand SVG text on Lossless OG / share imagery — Hack Bold gradient-filled h1, thin sans eyebrow, Poor Story handwritten note. Use whenever a generated OG image needs title/eyebrow/sub text composited on top before it ships (the empty-region zone from generate-consistent-og-images is the canvas this…
deck-iteration-workflow
The Lossless Group's workflow for developing slides-only Astro sites for fundraise processes, aligned with the calmstorm-decks project patterns and the iterative approach from the "Develop a Slides-only Astro Site for a Fundraise Process" specification. Use when creating or modifying slide decks, managing slide…
slide-target
Load the full working context for ONE DidiDecks slide (deck/variant/slot) so an agent can iterate on it slide-by-slide without re-explaining where things live. The first of the slide- skill family (target → improve → rank → decompose). Use whenever the user wants to work on a specific slide of a DidiDecks/Astro deck …