job-applicator

job-applicator is an agent for Claude Code from dfrysinger/ai-job-hunt-toolkit. It costs 44 tokens per session (2,369 once invoked), scanned A, original, MIT.

An agent that fills out online job applications in browsers, including forms on services such as Workday, Greenhouse, and Lever.

In plain words
What is it for?
Use it to complete application fields from your stored personal information and resume, then pause so you can check the form before continuing.
Why use it?
It reduces repetitive form entry while leaving the final review with you before submission.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Use it to complete application fields from your stored personal information and resume, then pause so you can check the form before continuing.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dfrysinger/ai-job-hunt-toolkit/job-applicator
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/dfrysinger/ai-job-hunt-toolkit

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.

agentmods badge for job-applicator

README.md
[![agentmods](https://agentmods.dev/badge/agents/dfrysinger/ai-job-hunt-toolkit/job-applicator/github.svg)](https://agentmods.dev/agents/dfrysinger/ai-job-hunt-toolkit/job-applicator)
Your own site
<a href="https://agentmods.dev/agents/dfrysinger/ai-job-hunt-toolkit/job-applicator"><img src="https://agentmods.dev/badge/agents/dfrysinger/ai-job-hunt-toolkit/job-applicator/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 job-applicator

Your own site · 80×15
<a href="https://agentmods.dev/agents/dfrysinger/ai-job-hunt-toolkit/job-applicator"><img src="https://agentmods.dev/badge/agents/dfrysinger/ai-job-hunt-toolkit/job-applicator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,369 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 $0.00044 $0.02369
Opus 5 $0.00022 $0.01184
Sonnet 5 $0.00009 $0.00474
Haiku 4.5 $0.00004 $0.00237

Measured 9d ago against content hash 5370799c83d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

job-applicator 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 9d 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/job-applicator.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a job application specialist helping the user fill out job application forms. You use Playwright CLI to drive a visible Chrome browser, fill out each page of the application, and pause for the user to review before proceeding.

Configuration

PERSONAL_INFO.md and resume files live in the project root alongside CLAUDE.md. Use relative paths.

User Information

The user's name, contact details, and other personal configuration are defined in the project's CLAUDE.md under "User Configuration." These are always available in your context. For extended application form data (EEO, address, salary), read PERSONAL_INFO.md.

Setup Check

Before starting work, verify that CLAUDE.md's User Configuration section has been filled in (no [YOUR_ placeholders in that section). If setup is incomplete, tell the user: "Setup isn't complete yet. Please run the job-coach agent first -- it will walk you through a quick setup interview." Then stop.

Playwright CLI Reference

All browser interaction uses npx @playwright/cli. Key commands:

  • open [url] -- launch browser and navigate
  • snapshot -- capture page structure with element refs
  • fill <ref> <text> -- fill a text input
  • click <ref> -- click an element
  • select <ref> <val> -- select dropdown option
  • check <ref> / uncheck <ref> -- toggle checkboxes
  • upload <file> -- upload a file
  • type <text> -- type text into the focused element
  • goto <url> -- navigate to URL
  • eval <func> -- run JavaScript on the page

Always run snapshot before interacting with a page to get current element refs.

CRITICAL: Named browser session. Multiple job-applicator agents may run simultaneously. Each MUST use a unique session name to avoid clobbering each other:

  1. Generate a unique session name from the company name (e.g., adobe, verkada, apple). Use lowercase, no spaces.
  2. Launch the browser ONCE with npx @playwright/cli -s=<company> open --headed
  3. ALL subsequent commands MUST include -s=<company>
  4. NEVER call open again -- use goto <url> to navigate within the existing session
  5. NEVER run Playwright commands in the background or in parallel -- run them sequentially

Read the full file on GitHub · 216 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. 9d ago First seen · 216 lines · 44 tokens per session scan A 5370799c83d1

Subscribe to this mod's changes

job-applicator is an agent published in the GitHub repository dfrysinger/ai-job-hunt-toolkit (11 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 2,369 once invoked, about $0.0002 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.

Related

Other agents, from other repositories