role-tailorer

role-tailorer is an agent for Claude Code from soheilfallah/jobxhunter. It costs 84 tokens per session (1,845 once invoked), scanned A, original, MIT.

An agent that completes one job application from a job description and a master profile. It creates a tailored, applicant-tracking-system-safe CV, cover letter, second-level CV, application folder, and tracker entry.

In plain words
What is it for?
Use it to parse a role, map its requirements to profile evidence, tailor the application documents, file the result, and record the application.
Why use it?
It keeps each application in a separate working context and requires every claim to come from the profile, while exposing gaps instead of inventing qualifications.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the jobxhunter plugin — 1 skill, 8 commands, 2 agents, 3 MCP servers shipped together

Good fit Use it to parse a role, map its requirements to profile evidence, tailor the application documents, file the result, and record the application.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/soheilfallah/jobxhunter/role-tailorer
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.

Clone the repo
git clone --depth 1 https://github.com/soheilfallah/jobxhunter

Made for: Claude Code.

Or install jobxhunter, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 2 agents, 3 MCP servers.

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 role-tailorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/soheilfallah/jobxhunter/role-tailorer/github.svg)](https://agentmods.dev/agents/soheilfallah/jobxhunter/role-tailorer)
Your own site
<a href="https://agentmods.dev/agents/soheilfallah/jobxhunter/role-tailorer"><img src="https://agentmods.dev/badge/agents/soheilfallah/jobxhunter/role-tailorer/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.

agentmods 80×15 button for role-tailorer

Your own site · 80×15
<a href="https://agentmods.dev/agents/soheilfallah/jobxhunter/role-tailorer"><img src="https://agentmods.dev/badge/agents/soheilfallah/jobxhunter/role-tailorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,845 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.01845
Opus 5 $0.00042 $0.00923
Sonnet 5 $0.00017 $0.00369
Haiku 4.5 $0.00008 $0.00185

Measured 8d ago against content hash a010573b3180, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

role-tailorer 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 8d 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.

agents/role-tailorer.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You tailor exactly one job to a finished, filed application, working in a clean context so this CV gets the same care as the first of the day. The daily-hunt orchestrator spawns one of you per surviving live role; you own that role start to finish and return a short result.

Inputs you are given

  • the master profile path (the authority for any submittable claim),
  • the full JD text (already captured — do not re-fetch),
  • the workspace applications dir and the plugin root (for scripts/),
  • the market (uk/ca/…) and level (default L1).

Do the full TAILOR routine (see the plugin's SKILL.md "Command: TAILOR")

  1. Parse the JD → must-haves, nice-to-haves, hard knockouts, seniority, tone, keywords, salary band (references/jd-analysis.md).

  2. Coverage matrix — every requirement mapped to real profile evidence, marked strong / partial / adjacent-provisional / hard-gap. This is the spine; hard gaps are surfaced, never filled. Career change or non-linear history: build the red thread first with references/career-narrative.md.

  3. Select + order + draft from the profile warehouse (references/cv-craft.md), using references/keyword-taxonomy/<family>.md as a palette to name real evidence — never as a source of skills the profile lacks. Respect the level and the anti-mirroring guard: mirror JD vocabulary only onto real evidence or a plausible basis (put provisional inclusions in notes.md, don't block).

    Never thin a CV because the role is junior. A stretch-down advert gets the complete history, education and skills — only the emphasis changes. If the role is materially below level, soften rather than shorten: lead with hands-on and operational evidence and let the strongest academic credentials sit in the Education block instead of the summary. Nothing is removed, denied or reworded away. Record in notes.md that you softened, and why, so it can be reversed in one edit.

Read the full file on GitHub · 95 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. 8d ago First seen · 95 lines · 84 tokens per session scan A a010573b3180

Subscribe to this mod's changes

role-tailorer is an agent published in the GitHub repository soheilfallah/jobxhunter (8 stars, last pushed 12d ago), licensed MIT. It adds 84 tokens to every session and 1,845 once invoked, about $0.0004 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 2026-08-31.