agentmods.dev

tailit CLAUDE.md

tailit CLAUDE.md is an instructions file for coding agents from sardorml/tailit. It costs 1,984 tokens per session, scanned A, original, MIT.

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

In plain words
What is it for?
Use them when developing or debugging Tailor, especially its job-link resume tailoring, profile creation, browser storage, Typst templates, and PDF or SVG rendering.
Why use it?
They give a coding agent the context needed to change the app consistently, without rediscovering how its resume editor, previews, and exports work.

Instructions file

not rated 22 2mo ago A scan 1,984 tokens original MIT
View the source file sardorml/tailit
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 instructions/sardorml/tailit/claude-md
Clone the repo
git clone --depth 1 https://github.com/sardorml/tailit

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 tailit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sardorml/tailit/claude-md.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.svg" alt="Measured on agentmods" 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. 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 $0.01984 $0.01984
Opus 5 $0.00992 $0.00992
Sonnet 5 $0.00397 $0.00397
Haiku 4.5 $0.00198 $0.00198

Measured 4d ago against content hash abcbcb5dea46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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.

  1. 4d 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 (22 stars, last pushed 2mo ago), licensed MIT. It adds 1,984 tokens to every session, about $0.0099 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.

ai-assisten-resmume-builderresumeresume-builderresume-tailor
Related

Other instructions, from other repositories

resume-builder AGENTS.md

Instructions for DaveVoyles/resume-builder, covering 🤖 agent instructions, 🚀 default workflow, ⚠️ claim rules, 🔒 privacy rules and 💬 communication style.

DaveVoyles/resume-builder · 1,314 tokens

reactive-resume copilot-instructions.md

Instructions for amruthpillai/reactive-resume: Respond terse like smart caveman. All technical substance stay. Only fluff die.

amruthpillai/reactive-resume · 184 tokens

reactive-resume AGENTS.md

Instructions for amruthpillai/reactive-resume, covering skill loading, graphify, agents.md, agent skills and ownership map.

amruthpillai/reactive-resume · 2,836 tokens

personal-site AGENTS.md

Instructions for mldangelo/personal-site, covering agents.md, quick commands, project structure, code style and git workflow.

mldangelo/personal-site · 3,656 tokens

vitaecontext AGENTS.md

AGENTS.md instructions for vitaecontext/vitaecontext, covering agents.md, scope, start here, source of truth and brand contract.

vitaecontext/vitaecontext · 717 tokens

vitaecontext copilot-instructions.md

Copilot instructions for vitaecontext/vitaecontext, covering repository instructions for github copilot, repository model, coding and documentation rules and validation.

vitaecontext/vitaecontext · 296 tokens