gsd-task-manager: Skill for Claude Code

.agents/skills/inkwell-retrofit/SKILL.md

inkwell-retrofit is a skill for Claude Code from vscarpenter/gsd-task-manager. It costs 48 tokens per session (796 once invoked), scanned A, original, MIT.

A guide for applying the Inkwell visual design system to an existing page, component, or standalone HTML document. It focuses on styling while preserving the current content and behavior.

In plain words
What is it for?
Use it to reskin pages, align Tailwind CSS projects with Inkwell tokens, update documentation or reports, and reuse existing colors, spacing, and components.
Why use it?
It reduces duplicate styling rules and prevents a retrofit from becoming an unrelated redesign.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is vscarpenter/gsd-task-manager's own configuration. It tells Claude Code how to work on gsd-task-manager itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gsd-task-manager configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vscarpenter/gsd-task-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vscarpenter/gsd-task-manager/main/.agents/skills/inkwell-retrofit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vscarpenter/gsd-task-manager

Made for: Claude Code.

Wrote 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.

agentmods badge for inkwell-retrofit

README.md
[![agentmods](https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/inkwell-retrofit/github.svg)](https://agentmods.dev/skills/vscarpenter/gsd-task-manager/inkwell-retrofit)
Your own site
<a href="https://agentmods.dev/skills/vscarpenter/gsd-task-manager/inkwell-retrofit"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/inkwell-retrofit/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.

agentmods 80×15 button for inkwell-retrofit

Your own site · 80×15
<a href="https://agentmods.dev/skills/vscarpenter/gsd-task-manager/inkwell-retrofit"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/inkwell-retrofit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 796 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00796
Opus 5.5 $0.00019 $0.00318
Sonnet 5.5 $0.00010 $0.00159
Haiku 4.5 $0.00005 $0.00080

Measured 2mo ago against content hash 6916c3c15320, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

inkwell-retrofit 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 2mo 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.

.agents/skills/inkwell-retrofit/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

inkwell-retrofit

Use this skill when an existing page, component, or standalone document needs to adopt Inkwell while preserving its content and behavior.

Good fits

  • Re-skin an existing page with Inkwell tokens and primitives.
  • Convert a standalone HTML explainer or report to the Inkwell visual system.
  • Remove duplicate token declarations or competing CSS shims.
  • Align a Tailwind v4 project with Inkwell's token and theme model.

Do not use this skill to redesign the product information architecture or rewrite content. The default move is visual alignment, not content invention.

First read

Before editing, read:

  1. AGENTS.md for project-specific styling rules.
  2. Existing Inkwell files under app/css/ and public/css/.
  3. Any sibling page already using Inkwell, such as a report or explainer.
  4. The target page/component end to end so content stays intact.

Core rules

  • Reuse existing Inkwell tokens before adding project-specific tokens.
  • Do not hardcode hex colors outside token definitions.
  • Prefer semantic tokens such as --ivory, --paper, --slate, --accent, --border, and --backdrop.
  • Keep one saturated accent unless the page truly needs data-viz hues.
  • Use Inkwell primitives where available: .card, .alert, .tbl, .tldr, .toc, .sec-head, .eyebrow, .badge, .chip-dot.
  • Preserve the 1.5px hairline convention unless the project explicitly documents a different value.
  • Keep typography roles consistent: serif for major headings and editorial callouts, mono for labels/file refs/code, sans for normal body UI.
  • Preserve dark-mode behavior through data-theme and tokens, not per-component ad hoc overrides.
  • SVG fills and strokes should reference tokens so diagrams theme correctly.

Retrofit steps

  1. Identify the current styling source: global CSS, inline styles, Tailwind utilities, standalone <style>, or linked CSS.
  2. Remove competing token systems only when Inkwell fully replaces them.
  3. Map existing colors, borders, typography, spacing, and callouts to Inkwell tokens and primitives.
  4. Keep app-specific extensions small, named, and layered after Inkwell imports.
  5. Replace hardcoded rgba/hex values with semantic tokens.
  6. Preserve content and IDs unless the task explicitly asks for content edits.
  7. Verify light and dark modes.
  8. Verify the page renders standalone if it was standalone before.

Read the full file on GitHub · 80 lines

Changes

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.

  1. 2mo ago First seen · 80 lines · 48 tokens per session scan A 6916c3c15320

Subscribe to this mod's changes

inkwell-retrofit is a skill published in the GitHub repository vscarpenter/gsd-task-manager (40 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 796 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 2026-08-30.

Related

Other skills, from other repositories

html-design-revision

Revise an existing HTML/CSS design file with small, safe edits. Use when asked to change a color, text, size, position or add an element to a design that already exists. Use other tools for building a design from scratch.

zenitheditor/zenith · 54 tokens

html-author

Build a finished one-page or multi-page design (flyer, letterhead, handout, deck, poster, menu, card, report, invoice) as a single HTML/CSS file at a fixed pixel size. Use when asked to design something from a brief, starting from nothing. Use other tools to edit an existing file.

zenitheditor/zenith · 70 tokens

site-header

Design and build the site-wide header (logo, menu, language switcher, cart, call to action) yourself, then have the site save it in the right places and check it. Activate whenever the user asks to create, fix, redesign, modernise, tidy or "make professional" a header or top navigation, or complains that the menu…

wppilot-labs/wordpress-mcp-elementor-wppilot · 98 tokens

section-rebuild

Build a page section in code using the values measured off a real site rather than guessing them from a screenshot. Use when the user wants to recreate, adapt or take inspiration from a hero, pricing table, FAQ, testimonial or any other section they have seen.

bryntay/a1-mcp · 56 tokens

block-theme

Change a block theme's look and structure the way the site editor does - Global Styles (colours, fonts, spacing), templates and template parts (header, footer, single, page), patterns and navigation menus - with undo. Activate when the user asks to change site-wide colours or fonts, edit the header, footer or a page…

wppilot-labs/wordpress-mcp-elementor-wppilot · 89 tokens

builder-quality

Check that an Elementor page an agent built or changed is easy for a person to edit afterwards - no layout pasted into HTML widgets, no inline styles or scripts, global colours instead of fixed ones, sensible nesting - and fix what it finds. Activate after building or redesigning an Elementor page, or when the user…

wppilot-labs/wordpress-mcp-elementor-wppilot · 78 tokens