A step-by-step process for submitting an authorised job application through supported job sites. It saves progress between steps and requires a confirmation receipt before recording the application as sent.

Use it to detect a form, fill it in, upload a CV, answer screening questions, review the result, and submit when the application is authorised.

It prevents blind retries and duplicate submissions after crashes or uncertain results. A revoked approval or unknown outcome stops the process for human attention.

apply-flow — Skill for Claude Code by leopu00/job-hunter-team

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/leopu00/job-hunter-team

agentmods

npx agentmods add skills/leopu00/job-hunter-team/apply-flow

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/skills/leopu00/job-hunter-team/apply-flow/github.svg)](https://agentmods.dev/skills/leopu00/job-hunter-team/apply-flow)

Your own site

<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/apply-flow"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/apply-flow/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/skills/leopu00/job-hunter-team/apply-flow"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/apply-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,533 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.

Model	Per session	Once invoked
Fable 5.1	$0.00085	$0.04533
Opus 5.5	$0.00034	$0.01813
Sonnet 5.5	$0.00017	$0.00907
Haiku 4.5	$0.00009	$0.00453

Measured 1mo ago against content hash 1132fcb55473, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

apply-flow 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 1mo 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/_skills/apply-flow/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

python3 /app/shared/skills/apply_flow.py \
  --position-id "$PID" \
  --url "$URL" \
  --profile "$JHT_HOME/profile/candidate_profile.yml" \
  --cv "$CV"

Give this command a timeout of at least 10 minutes: a LinkedIn sign-in can wait up to 5 minutes in the browser for the verification code the user sends on Telegram, and a command killed while it waits leaves the code request to expire.

PID, URL and CV come from the latest apply_gate.py queue read (skill apply-authorization), never from memory.

The state machine

detect → fill → upload_cv → screening → review → submit → applied
                                                        ↘ blocked_human

Every completed step is saved to a checkpoint ($JHT_HOME/.cache/apply-flow/<id>.json). After a crash the flow resumes where it was: filling is replayed, the click is not.
submit_started is saved before the click. If a process dies after that line, the outcome is unknown, and an unknown outcome is never clicked again: the flow checks the page for a confirmation and, without one, blocks with submit_outcome_unknown.
The gate is checked at start and immediately before the click. A flag revoked while the form was being filled stops the submission.
Three complete recipes today: Ashby, Greenhouse (only its three public hosts, job-boards.greenhouse.io, job-boards.eu.greenhouse.io, boards.greenhouse.io, over HTTPS; the page is re-checked after every step) and Lever (only jobs.lever.co and jobs.eu.lever.co, over HTTPS, re-checked the same way). LinkedIn: "apply on company website" continues on that site with its recipe; Easy Apply signs in with the user's account (session kept, verification code on Telegram) and walks the dialog. Any other platform blocks for a human.

The receipt

applied is written only when the flow holds both:

a screenshot of the confirmation page, and
a confirmation URL or confirmation text.

Read the full file on GitHub · 158 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · +12 lines 1132fcb55473
1mo ago Changed · +45 lines f42db23df566
1mo ago First seen · 101 lines · 85 tokens per session scan A 773f151a899c

Subscribe to this mod's changes

apply-flow is a skill published in the GitHub repository leopu00/job-hunter-team (52 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 4,533 once invoked, about $0.0003 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 2026-09-14.

Productivity ai ai-agents artificial-intelligence automation career cli

freehire-mail-triage

Use when sorting a job seeker's application mail into the freehire tracker from their own mail client (himalaya, mbsync, notmuch, the Gmail API, any IMAP) — pushing a fetched batch, judging what each message is, linking it to an application, advancing a stage from a reply, or draining the two queues the matcher fills…

strelov1/freehire-cli · 96 tokens

using-freehire

Use when orienting in the freehire CLI as a whole — installing it, authenticating with an API key, working out which of its surfaces answers a job seeker's question, or troubleshooting a 401. The task skills do the work; this one is the map and the setup.

strelov1/freehire-cli · 64 tokens

yc-job-tracker

Track and filter YC startup job listings for AI/ML engineering roles. Builds a daily-refreshed local database of relevant jobs with scoring and alerts for new postings.

chandrudp29/skillhub · 38 tokens

gws-gmail-send

Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.

googleworkspace/cli · 13 tokens

obsidian-bases

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

kepano/obsidian-skills · 63 tokens

gws-gmail-watch

Gmail: Watch for new emails and stream them as NDJSON.

googleworkspace/cli · 20 tokens

apply-flow