Borrowing it
Nothing to install: this file belongs to sherifkozman/uicontract. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sherifkozman/uicontract/main/CLAUDE.mdgit clone --depth 1 https://github.com/sherifkozman/uicontractWrote 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/instructions/sherifkozman/uicontract/claude-md)<a href="https://agentmods.dev/instructions/sherifkozman/uicontract/claude-md"><img src="https://agentmods.dev/badge/instructions/sherifkozman/uicontract/claude-md/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/instructions/sherifkozman/uicontract/claude-md"><img src="https://agentmods.dev/badge/instructions/sherifkozman/uicontract/claude-md.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 | $0.04106 | $0.04106 |
| Opus 5.5 | $0.01642 | $0.01642 |
| Sonnet 5.5 | $0.00821 | $0.00821 |
| Haiku 4.5 | $0.00411 | $0.00411 |
Grade A, and why
uicontract CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UIC Contributor Contract
UIC (UI Contracts) is a CLI tool and agent skill that makes web app UIs machine-readable. It parses source code to discover interactive elements, names them with stable hierarchical IDs, annotates source with data-agent-id attributes, generates a manifest describing the UI surface, and provides a CI diff gate for breaking changes. Think of it as OpenAPI for UIs. It is NOT a runtime library, NOT an MCP server, and NOT a browser extension.
Spec: docs/SPEC.md
Architecture: docs/ARCHITECTURE.md
Milestones: docs/MILESTONES.md
Benchmarks: docs/BENCHMARKS.md
1. Critical Rules
Every PR Must
- Pass
pnpm build && pnpm lint && pnpm testwith zero errors and zero warnings. - Pass
npx uicontract diffon UIC's own fixture manifests (dogfooding). If fixture manifests change, the diff must be reviewed and committed intentionally. - Include tests for any new or changed behavior. No exceptions.
- Have zero
anytypes. Useunknown+ type narrowing instead. - Not add a dependency without a justification comment in the PR description explaining why it's necessary and what alternatives were considered.
Every New CLI Command Must Have
- Unit tests for argument parsing and output formatting
- Integration test with fixture data
--helptext that documents all flags--jsonoutput flag for machine consumption- Entry in
docs/CLI.md
Every New Parser Must Have
- Unit tests for each element type it discovers
- Golden file tests with a fixture app
- Integration test: scan -> annotate -> re-scan -> verify round-trip
- Entry in
docs/PARSERS.md
TypeScript
strict: truein all tsconfigsnoUncheckedIndexedAccess: truenoImplicitReturns: true- No
any. No@ts-ignore.@ts-expect-erroronly with a comment explaining the bug being worked around. - Prefer
interfaceovertypefor object shapes. Usetypefor unions, intersections, and mapped types.
2. Decision Framework
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 · 419 lines · 4,106 tokens per session scan A e3ae3ec3d9c1
uicontract CLAUDE.md is an instructions file published in the GitHub repository sherifkozman/uicontract (5 stars, last pushed 5mo ago), licensed MIT. It adds 4,106 tokens to every session, about $0.0164 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.
uicontract CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| uicontract CLAUDE.mdsherifkozman/uicontract | Instructions file | 5 | 5mo ago | MIT | A | 4,106 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 280k | 2d ago | MIT | A | 4,325 | Codex, OpenCode |