What is tailit CLAUDE.md?

Project instructions for Tailor, an AI resume-writing web app. They describe its technologies, resume workflow, PDF export, and project conventions.

Use them when developing or debugging Tailor, especially its job-link resume tailoring, profile creation, browser storage, Typst templates, and PDF or SVG rendering.

They give a coding agent the context needed to change the app consistently, without rediscovering how its resume editor, previews, and exports work.

How sardorml/tailit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sardorml/tailit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sardorml/tailit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sardorml/tailit

Made for: Claude Code.

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/instructions/sardorml/tailit/claude-md/github.svg)](https://agentmods.dev/instructions/sardorml/tailit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sardorml/tailit/claude-md"><img src="https://agentmods.dev/badge/instructions/sardorml/tailit/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sardorml/tailit/claude-md"><img src="https://agentmods.dev/badge/instructions/sardorml/tailit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,984 This file is loaded in full into every session.

When invoked 1,984 The same file — it is already loaded in full.

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	$0.01984	$0.01984
Opus 5.5	$0.00794	$0.00794
Sonnet 5.5	$0.00397	$0.00397
Haiku 4.5	$0.00198	$0.00198

Measured 2mo ago against content hash abcbcb5dea46, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tailit 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.

CLAUDE.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@AGENTS.md

Tailor — project notes

AI resume-tailoring web app. Paste a job link → AI rewrites the user's resume to match it. An AI interview (or PDF/DOCX upload) builds the profile; export ATS-friendly PDFs.

Stack

Next.js 16 (App Router) · React 19 · TypeScript · Ant Design v6 (stock theme; no Tailwind)
Groq free API (open-source Llama/Qwen) via src/lib/llm/provider.ts — key is server-side only
Zustand + persist (localStorage) — no backend DB, no auth (data stays in the browser)
Typst for PDF templates/export — compiled server-side via @myriaddreamin/typst-ts-node-compiler (src/lib/typst/, POST /api/render). The compiler is a process-global singleton, warmed at boot in src/instrumentation.ts so the first render is ms not ~2s. The export/download uses the PDF; the live preview uses format:"svg" (Typst's own renderer → vector glyph outlines), shown as an <img> — same layout engine as the PDF so it's pixel-identical to the export, but rasterized to a single composited layer so it scrolls smoothly and stays crisp at any width (a re-implementation like pdf.js mis-renders embedded-font ligatures; a native PDF plugin re-rasterizes on every scroll frame → lag). · unpdf/mammoth for upload parsing · linkedom + @mozilla/readability + Jina Reader for job scraping

UI components

Ant Design v6 is the UI system — every component comes from antd (stock theme, no token overrides), icons from @ant-design/icons. There is no Tailwind, no custom primitives, no CSS-in-JS theme config.

SSR is wired via @ant-design/nextjs-registry: src/app/layout.tsx (server) wraps the tree in <AntdRegistry> → src/app/providers.tsx ("use client") = <ConfigProvider> → antd <App>. The <App> wrapper supplies context for the static message/modal APIs — get them with const { modal, message } = App.useApp().
Any file using antd components must be a Client Component ("use client") — antd calls createContext at module load, which breaks in Server Components (only layout.tsx may import AntdRegistry, never antd UI).
Layout/structure uses antd primitives (Layout, Flex, Space, Row/Col) + the style prop for one-offs; brand/accent color comes from theme.useToken().token.colorPrimary (stock antd blue), never hardcoded.
src/app/globals.css is plain CSS (no Tailwind) with only a few helpers: .screen-lg (desktop one-viewport: height:100dvh;overflow:hidden ≥1024px), .scrollbar-thin, .no-scrollbar, .pdf-canvas (dark #525659).

Read the full file on GitHub · 57 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.

2mo ago First seen · 57 lines · 1,984 tokens per session scan A abcbcb5dea46

Subscribe to this mod's changes

tailit CLAUDE.md is an instructions file published in the GitHub repository sardorml/tailit (30 stars, last pushed 4mo ago), licensed MIT. It adds 1,984 tokens to every session, about $0.0079 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.

ai-assisten-resmume-builder resume resume-builder resume-tailor

tailit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tailit CLAUDE.mdsardorml/tailit	Instructions file	30	4mo ago	MIT	A	1,984	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

tailit: Instructions file for Claude Code