agentmods.dev

validate-fidelity

validate-fidelity is a skill for Claude Code from big-emotion/agent-atelier. It costs 41 tokens per session (2,625 once invoked), scanned A, original, MIT.

A checking tool for comparing a written interface specification and a working website with reference data and screenshots of the original interface.

In plain words
What is it for?
Use it to check specifications, visual details, or both. You can check a whole website or focus on one component, such as a sidebar.
Why use it?
It finds differences between the planned, original, and built interface before those differences reach users.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the frontend-fidelity plugin — 3 skills shipped together

not rated 3repo 24d ago A scan 41 tokens original MIT

Good fit Use it to check specifications, visual details, or both. You can check a whole website or focus on one component, such as a sidebar.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/big-emotion/agent-atelier/validate-fidelity
View source ↗ big-emotion/agent-atelier
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.

Any agent
npx skills add big-emotion/agent-atelier --skill validate-fidelity
Clone the repo
git clone --depth 1 https://github.com/big-emotion/agent-atelier

Made for: Claude Code.

Or install frontend-fidelity, the plugin that ships this one along with the rest of its 3 skills.

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 validate-fidelity

README.md
[![agentmods](https://agentmods.dev/badge/skills/big-emotion/agent-atelier/validate-fidelity/github.svg)](https://agentmods.dev/skills/big-emotion/agent-atelier/validate-fidelity)
Your own site
<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/validate-fidelity"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/validate-fidelity/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 validate-fidelity

Your own site · 80×15
<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/validate-fidelity"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/validate-fidelity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,625 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.
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 $0.00041 $0.02625
Opus 5.5 $0.00016 $0.01050
Sonnet 5.5 $0.00008 $0.00525
Haiku 4.5 $0.00004 $0.00263

Measured 2mo ago against content hash e14716102d44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validate-fidelity 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.

plugins/frontend-fidelity/skills/validate-fidelity/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate Fidelity — Spec & Visual Drift Detection

Compare specs and running implementations against the reverse-UI oracle to catch drift before it ships.

Input: $ARGUMENTS = --phase <spec|visual|all> [--domain <NNN-name>] [--focus <component>] [--oracle <path>]

Arguments

  • --phase (required): spec | visual | all
    • spec — validate spec document against oracle JSON data
    • visual — validate running app against oracle screenshots + structure
    • all — run both phases sequentially for all matching domains
  • --domain (optional): spec number or name, e.g., 004-home, 002-app-shell. If omitted, validates all domains that have both a spec and an oracle source.
  • --focus (optional): component name to narrow scope, e.g., sidebar, module-card. Only validates requirements related to this component.
  • --oracle (optional): path to reverse-UI output directory. Auto-detected if omitted.

Examples

/validate-fidelity --phase spec --domain 004-home
/validate-fidelity --phase visual --domain 004-home
/validate-fidelity --phase all
/validate-fidelity --phase spec --domain 002-app-shell --focus sidebar
/validate-fidelity --phase spec --oracle ./reverse-ui-localhost-3000

Phase 0: Parse Input & Locate Oracle

  1. Parse $ARGUMENTS for --phase, --domain, --focus, --oracle.
  2. If --phase is missing, ask the user which phase to run.
  3. Locate the oracle in this priority order: a. --oracle flag (explicit path) b. specs/assets/manifest.json → read meta.baseUrl to derive reverse-ui-{domain}/ c. Glob for reverse-ui-*/manifest.json in current working directory d. Ask user if not found
  4. Verify the oracle directory exists and contains manifest.json.
  5. If --domain is specified, locate the corresponding spec file: specs/{domain}.md
  6. If --domain is omitted, glob for all specs/*.md files and match each to an oracle page directory.
  7. Check for component-kit availability: component-kit-{domain}/manifest.json — if present, use it for more precise validation.

Read the full file on GitHub · 257 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 · 257 lines · 41 tokens per session scan A e14716102d44

Subscribe to this mod's changes

validate-fidelity is a skill published in the GitHub repository big-emotion/agent-atelier (3 stars, last pushed 24d ago), licensed MIT. It adds 41 tokens to every session and 2,625 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 2026-08-31.

CI and CDClaude CodeDesign and UXTestingatlassianclaude-code-pluginconventional-commitsdeveloper-tooling
Related

validate-fidelity compared with skills from other repositories

validate-fidelity next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
validate-fidelitybig-emotion/agent-atelierSkill324d agoMITA41Claude Code
prototypetoBzh30/Claude-Project-BootstrapSkill33mo agoMITA90Claude Code
top-designwondelai/skillsSkill2.6k5d agoMITA113Claude Code, Codex
configure-env-variablesmicrosoft/power-platform-skillsSkill1.1kyesterdayMITA119Claude Code
sxonowork-studio/notfair-pluginSkill4.1kyesterdayMITA211Claude Code
influence-psychologywondelai/skillsSkill2.6k5d agoMITA156Claude Code
ux-heuristicswondelai/skillsSkill2.6k5d agoMITA122Claude Code, Codex