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 thierryc/Glyphs-mcp --skill glyphs-curve-repairgit clone --depth 1 https://github.com/thierryc/Glyphs-mcpWrote 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/thierryc/glyphs-mcp/glyphs-curve-repair)<a href="https://agentmods.dev/skills/thierryc/glyphs-mcp/glyphs-curve-repair"><img src="https://agentmods.dev/badge/skills/thierryc/glyphs-mcp/glyphs-curve-repair/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/thierryc/glyphs-mcp/glyphs-curve-repair"><img src="https://agentmods.dev/badge/skills/thierryc/glyphs-mcp/glyphs-curve-repair.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 | $0.00046 | $0.00691 |
| Opus 5.5 | $0.00018 | $0.00276 |
| Sonnet 5.5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
glyphs-curve-repair 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 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.
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.
What it actually says
Curve Inspector · Inspect & Repair
Use the installed Curve Inspector engine, never recreate its formulas in a script. This skill package ships with the companion; managed-catalog registration is deferred until a release can pin its actual source commit.
Resolve the intended document, glyph, owning layer and foreground/background
surface. Select shared on-curve nodes only: both adjoining segments are included
automatically. Bind joins once as zero-based (path, node) pairs. Repair
analysis is independent of the Reporter's 128-cubic display cap.
Default to native-star and maxDeviationEm=0.001. Stars preserve stored
coordinates while changing the effective outline. The same native method uses
stars between curves and raindrops between lines and curves, in either direction.
supertool-handles supports curve/curve joins only and is the
explicit fixed-on-curve alternative; tunniBalance defaults to false and its
result must still pass G2 and neighbor checks. Preserve corners and locks.
Use run_repair.py through the existing advertised
python_script workflow. The helper imports the installed shared engine and
checks its version; a missing companion is an installation gap, not permission
to copy an algorithm into the script. Choose operation=analyze or propose
for preview-only requests. operation=repair recomputes and applies a guarded
proposal under existing repair authorization, then verifies actual native output.
Carry expectedFingerprint from a reviewed proposal into application.
Provide joins, allJoins, allLayers, method, maxDeviationEm,
tunniBalance and optional region as needed. region is an explicit list of
[minimum,maximum] pairs in the font's native axis order. Report the declared
region, families, expected/evaluated locations, maximum continuous outline
bound, its reported metric, and effective join movement. Fixed-correspondence
cubics retain the exact squared-difference integral; native expanded chains
report that integral as null. Report generated-segment G1 separately from G2 at
the requested source join and from drawing-grid quantization. The 4096-location
limit never truncates. A blocked mixed selection must be explained, not silently
reduced to an eligible subset.
Use native and recovery notes when executing
or explaining a refusal. Use the existing qualified dekink-native workflow
for HOI-specific trajectory problems; it is distinct from this G2 operation.
Do not claim general conditional-family or export qualification from ordinary
master tests. An unsupported family must remain a visible refusal.
V2 owns document identity and script jobs. Respect its saved-baseline rules. Native script restoration reloads the whole saved font and discards later unsaved changes; it is not selective patch rollback. Preview-only authorization does not authorize live edits, Save, installation or restart. Existing repair authorization need not be requested again for the same guarded scope.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 56 lines · 46 tokens per session scan A 2c1e0aa98f95
glyphs-curve-repair is a skill published in the GitHub repository thierryc/Glyphs-mcp (54 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 691 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.