A way to give web-app controls stable names that an automated agent can find, such as buttons, forms, and settings. It uses a manifest file and identifiers attached to page elements.

Use it to scan a web app, name its interactive elements, search for a control, inspect its details, or compare the element manifest between versions.

Browser automation based on fragile selectors can break when the page structure changes. Stable names make it easier to locate and target the intended control.

uic — Skill for Claude Code and Codex by sherifkozman/uicontract

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 sherifkozman/uicontract --skill skill

Clone the repo

git clone --depth 1 https://github.com/sherifkozman/uicontract

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sherifkozman/uicontract/skill/github.svg)](https://agentmods.dev/skills/sherifkozman/uicontract/skill)

Your own site

<a href="https://agentmods.dev/skills/sherifkozman/uicontract/skill"><img src="https://agentmods.dev/badge/skills/sherifkozman/uicontract/skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sherifkozman/uicontract/skill"><img src="https://agentmods.dev/badge/skills/sherifkozman/uicontract/skill.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 1,781 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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.01781
Opus 5.5	$0.00019	$0.00712
Sonnet 5.5	$0.00010	$0.00356
Haiku 4.5	$0.00005	$0.00178

Measured 2mo ago against content hash 919543019781, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uic 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.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/skill-validation.test.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/skill/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Contracts for Agent Automation

UI Contracts makes web app UIs machine-readable with stable hierarchical IDs, so agents can find, target, and interact with any interactive element by name instead of fragile selectors.

Quick Start

npx uicontract scan ./src -o manifest.json
npx uicontract name manifest.json -o manifest.json
npx uicontract find "login" --json
npx uicontract describe <agent-id> --json
npx uicontract list --type button --json
npx uicontract diff old.json new.json --json

Core Workflow

1. Discover

Check for an existing manifest.json in the project root. If none exists, generate one:

npx uicontract scan ./src -o manifest.json
npx uicontract name manifest.json -o manifest.json

2. Find

Search for elements by description. Fuzzy matching is enabled by default:

npx uicontract find "pause subscription" --json
npx uicontract find "pase subscribtion" --json   # fuzzy match still finds it
npx uicontract find "billing" --type button --json

3. Target

Use the agentId from the find result to target the element in the browser.

agent-browser:

# Scoped snapshot to find the element ref:
agent-browser snapshot -s '[data-agent-id="settings.billing.pause-subscription.button"]'
# Returns: - button "Pause subscription" [ref=e1]

# Interact using the ref:
agent-browser click @e1

CSS selector (any tool):

[data-agent-id="settings.billing.pause-subscription.button"]

Playwright MCP: Launch with --test-id-attribute=data-agent-id, then use ref values from the accessibility snapshot.

See references/browser-tool-bridge.md for all supported tools.

4. Verify

Compare the current manifest against a baseline to detect breaking changes:

npx uicontract diff baseline.json current.json --json

Exit code 1 means breaking changes were found.

Commands

Discovery

scan -- Discover interactive elements in source code.

Read the full file on GitHub · 233 lines

Files

What ships with it

7 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.

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.

2mo ago First seen · 233 lines · 48 tokens per session scan A 919543019781

Subscribe to this mod's changes

uic is a skill published in the GitHub repository sherifkozman/uicontract (5 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 1,781 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.

Browser automation

uic next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
uicsherifkozman/uicontract	Skill	5	5mo ago	MIT	A	48	Claude Code, Codex
interactive-loginyc-software/qm	Skill	16k	yesterday	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	yesterday	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	yesterday	MIT	A	40	Claude Code