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 dgk-dev/dgk-gpt --skill fdgit clone --depth 1 https://github.com/dgk-dev/dgk-gptWrote 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/dgk-dev/dgk-gpt/fd)<a href="https://agentmods.dev/skills/dgk-dev/dgk-gpt/fd"><img src="https://agentmods.dev/badge/skills/dgk-dev/dgk-gpt/fd/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/dgk-dev/dgk-gpt/fd"><img src="https://agentmods.dev/badge/skills/dgk-dev/dgk-gpt/fd.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 | $0.00058 | $0.01788 |
| Opus 5.5 | $0.00023 | $0.00715 |
| Sonnet 5.5 | $0.00012 | $0.00358 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
fd 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 1mo 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FD
Use this as a frontend design and polish mode. The goal is not to make every UI louder; the goal is to make it feel intentionally designed.
Claude-First Mode
If local claude CLI is available, treat it as the design specialist for meaningful frontend work instead of relying on Codex's taste alone.
- Use a single default workflow: delegate the first pass with
claude-design-bridge fd --apply, then inspect Claude's diff, fix any integration issues, and run verification yourself. - Only use
claude-design-bridge fd --planwhen the user explicitly wants critique-only guidance without edits, or when apply mode is clearly unsafe for the task. - Include the user request, relevant paths, constraints, and any established design language in the delegated prompt.
- Treat Claude's visual direction and implementation choices as the primary design authority, then use Codex to inspect, integrate, test, and clean up.
- Fall back to Codex-native design work only if the bridge is unavailable, unauthenticated, or clearly fails.
Post-Claude Audit
When Claude handled the first implementation pass, Codex should assume responsibility for the final integration quality.
- review the actual diff instead of trusting the visual pass blindly
- fix truncation, overflow, wrapping, density, spacing collisions, and awkward responsive breakpoints
- check keyboard/focus states, aria state integrity, and reduced-motion or contrast regressions when relevant
- preserve filtering, routing, data flow, and existing interaction logic unless the user explicitly asked for behavior changes
- catch SSR, hydration, typing, lint, and small-but-important maintainability issues that a design-first pass may miss
- keep the design intent, but tighten the engineering finish
Default Taste
Unless the user explicitly asks for a different direction, bias the design toward:
- Apple HIG-style clarity and restraint
- Jony Ive-style product thinking: simple, refined, modern, reduced, calm
- crisp hierarchy, generous spacing, careful materials, subtle motion, and high legibility
- elegance through reduction, not decoration
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.
- 1mo ago First seen · 173 lines · 58 tokens per session scan A 82cd3947d2a2
fd is a skill published in the GitHub repository dgk-dev/dgk-gpt (55 stars, last pushed 7mo ago), licensed MIT. It adds 58 tokens to every session and 1,788 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.
Other skills, from other repositories
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
ambience-skill
Layer A ambience-and-typographic-motion reference anchored to the react-bits catalog (reactbits.dev). Stacks on any style skill whenever work adds a hero atmosphere, an animated or shader background, a typographic reveal (split, blur, shimmer, typewriter, count-up, marquee), scroll storytelling, or card surface…
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
design-color
Add strategic color to monochromatic or dull interfaces using oklch for perceptually uniform palettes. Generates harmonious color systems with automatic light/dark variants and accessible contrast ratios.