agent-hephaestus

agent-hephaestus is a skill for Claude Code, Codex from Sistema2D/FrameCode-VibeWork. It costs 15 tokens per session (576 once invoked), scanned A, original, Apache-2.0.

An agent profile for making one focused improvement to a user interface, including accessibility, keyboard use, labels, empty states, and visual consistency.

In plain words
What is it for?
Use it when reviewing or improving interface details such as focus states, semantic HTML, contrast, interaction clarity, or microcopy.
Why use it?
It provides a defined review process for finding a small usability problem without changing unrelated behavior.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sistema2d/framecode-vibework/agent-hephaestus
Any agent
npx skills add Sistema2D/FrameCode-VibeWork --skill agent-hephaestus
Clone the repo
git clone --depth 1 https://github.com/Sistema2D/FrameCode-VibeWork

Made for: Claude Code, Codex.

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 agent-hephaestus

README.md
[![agentmods](https://agentmods.dev/badge/skills/sistema2d/framecode-vibework/agent-hephaestus.svg)](https://agentmods.dev/skills/sistema2d/framecode-vibework/agent-hephaestus)
Your own site
<a href="https://agentmods.dev/skills/sistema2d/framecode-vibework/agent-hephaestus"><img src="https://agentmods.dev/badge/skills/sistema2d/framecode-vibework/agent-hephaestus.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00576
Opus 5 $0.00008 $0.00288
Sonnet 5 $0.00003 $0.00115
Haiku 4.5 $0.00002 $0.00058

Measured 4d ago against content hash f6836420779a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-hephaestus 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 4d 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.

FCVW/skills/agent-hephaestus/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL: Agent Hephaestus

Purpose

UX/UI-focused agent profile for one small, safe, high-value accessibility, usability, or interface consistency improvement. It can run on demand or under an external scheduler; the scheduler is optional.

Activation Triggers

Load when the task involves UX polish, accessibility, semantic HTML, keyboard flow, focus state, labels, empty states, interaction clarity, visual consistency, UI microcopy, or the Portuguese equivalents: UI, interface, polir UI, refinar interface, consistência visual, acessibilidade, contraste, foco, navegação por teclado, estados vazios, estado de erro, labels, or microcopy.

Mission

Find and implement exactly one focused UX/accessibility improvement that preserves product behavior unless the existing behavior is inaccessible or misleading.

Mandatory Governance

  • Follow AGENTS.md, DESIGN.md, PLANNING.md, and TESTS.md.
  • Create or use an active plan before modifying files.
  • Update changelog and validation evidence before closure.
  • For durable codebase-specific UX learning, update a canonical page or create a sourced fcvw/wiki@1 page under wiki/agents/ with a collision-resistant ID; do not rely on a shared fixed journal filename.

Boundaries

Stop before implementation if the improvement requires:

  • new dependencies;
  • new design tokens, themes, or typography systems;
  • routing or information-architecture changes;
  • backend, security, or performance architecture changes;
  • broad refactoring or redesign.

Audit Order

  1. Accessibility labels, roles, focus, keyboard, and contrast.
  2. Interaction states: loading, disabled, error, empty, success.
  3. Alignment, spacing, hierarchy, and repetition against DESIGN.md.
  4. Microcopy clarity for the selected workflow.

Output Required

## Hephaestus UX Pass

- Skill loaded: `skills/agent-hephaestus/SKILL.md`
- Improvement selected:
- User value:
- Files in scope:
- Accessibility/design check:
- Validation:
- Knowledge update: `yes` / `no`

Read the full file on GitHub · 71 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. 4d ago First seen · 71 lines · 15 tokens per session scan A f6836420779a

Subscribe to this mod's changes

agent-hephaestus is a skill published in the GitHub repository Sistema2D/FrameCode-VibeWork (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 15 tokens to every session and 576 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

evaluate-pattern-adoption

Run or plan this repository's pattern-adoption evidence evaluation locally with signed-in Codex agents. Use when asked to refresh stale evidence, assess stable or exploratory patterns, evaluate one or all catalog patterns, discover possible new patterns, or prepare a reviewable evidence PR without model-backed GitHub…

PaulDuvall/ai-development-patterns · 68 tokens

design-to-code

Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…

yonatangross/orchestkit · 86 tokens

design-context-extract

Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…

yonatangross/orchestkit · 84 tokens

design-import

Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…

yonatangross/orchestkit · 74 tokens

component-search

Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system…

yonatangross/orchestkit · 57 tokens

design-ship

One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…

yonatangross/orchestkit · 84 tokens