What is resume-tailor-plugin CLAUDE.md?

Repository guidance for Claude Code and Codex plugin development, describing the resume-tailor plugin's structure and its resume-customisation workflow. An ATS is a hiring system that scans resumes for job-related terms and formatting.

Maintaining the resume-tailor skill, its plugin manifests, resume templates, ATS rules, and language-specific guidance.

It helps the coding agent follow the project's prompt-based design and understand where each instruction and reference file belongs.

resume-tailor-plugin CLAUDE.md — Instructions file by olegvg

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/olegvg/resume-tailor-plugin/claude-md

Clone the repo

git clone --depth 1 https://github.com/olegvg/resume-tailor-plugin

Per session 636 This file is loaded in full into every session.

When invoked 636 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.

Model	Per session	Once invoked
Fable 5	$0.00636	$0.00636
Opus 5	$0.00318	$0.00318
Sonnet 5	$0.00127	$0.00127
Haiku 4.5	$0.00064	$0.00064

Measured yesterday against content hash 5afb573c3cf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resume-tailor-plugin 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 yesterday.

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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Claude Code and Codex plugin (not a traditional software project) that provides a single skill: resume-tailor. It tailors resumes to specific job descriptions with ATS optimization. No build system, no tests, no dependencies — the project is entirely prompt-based markdown.

Architecture

.claude-plugin/plugin.json    — Claude Code plugin manifest (name, version, metadata)
.codex-plugin/plugin.json     — Codex plugin manifest and marketplace metadata
.agents/plugins/marketplace.json — Codex self-hosted marketplace index
skills/resume-tailor/
  SKILL.md                    — Main skill definition (workflow, stages, rules)
  references/
    ats-rules.md              — ATS formatting rules, keyword strategy, scoring formula
    locale-en.md              — English/US resume conventions
    locale-ru.md              — Russian/CIS resume conventions
    section-templates.md      — Section templates with slot markers for both locales

SKILL.md is the orchestrator — it defines a 7-stage workflow (Stages 0-6) and references the files in references/ at specific stages.
Reference files are read by the skill at runtime, not by the plugin system. They contain domain knowledge, not code.
The skill produces output in docs/resume/ within the user's project (master profile, drafts, DOCX files). This directory is not part of the plugin itself.

Key Concepts

Master profile (docs/resume/master-profile.md in user's project): comprehensive career data store, created on first run, reused across tailoring sessions.
Visibility system: roles in the master profile can be tagged always, variant-specific, on-request, or reference-only to control inclusion per resume variant.
ATS scoring: weighted formula (40% required skills, 20% nice-to-have, 20% quantification, 10% completeness, 10% distribution).
Locale support: EN/US and RU/CIS with different section ordering, personal info rules, and tone.

Read the full file on GitHub · 50 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.

yesterday First seen · 50 lines · 636 tokens per session scan A 5afb573c3cf4

Subscribe to this mod's changes

resume-tailor-plugin CLAUDE.md is an instructions file published in the GitHub repository olegvg/resume-tailor-plugin (38 stars, last pushed 4mo ago), licensed MIT. It adds 636 tokens to every session, about $0.0032 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.

Planning Productivity Research ats career cover-letter cv hiring job-application

resume-tailor-plugin CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Project Overview

Architecture

Key Concepts

What this file has done since we first saw it

Other instructions, from other repositories

ai-job-search CLAUDE.md

ai-job-search AGENTS.md

Resume-Builder CLAUDE.md

Resume-Builder AGENTS.md

job-application-mcp CLAUDE.md

claude-job-slayer CLAUDE.md