freehire-track-applications

freehire-track-applications is a skill for Claude Code from strelov1/freehire-cli. It costs 81 tokens per session (653 once invoked), scanned A, original, MIT.

A command-line tool for recording and reviewing job applications in freehire, an application-tracking service. It stores saved jobs, application stages, notes, and related follow-up information.

In plain words
What is it for?
Marking jobs as applied, bookmarking them, changing stages from application through offer or rejection, adding notes, listing tracked jobs, and reporting postings that never replied.
Why use it?
It prevents application details from being scattered across bookmarks, notes, and memory. It provides one view of what has been saved or applied to and where each application stands.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the freehire plugin — 6 skills, 5 commands shipped together

Good fit Marking jobs as applied, bookmarking them, changing stages from application through offer or rejection, adding notes, listing tracked jobs, and reporting postings that never replied.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/strelov1/freehire-cli/freehire-track-applications
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.

Any agent
npx skills add strelov1/freehire-cli --skill freehire-track-applications
Clone the repo
git clone --depth 1 https://github.com/strelov1/freehire-cli

Made for: Claude Code.

Or install freehire, the plugin that ships this one along with the rest of its 6 skills, 5 commands.

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 freehire-track-applications

README.md
[![agentmods](https://agentmods.dev/badge/skills/strelov1/freehire-cli/freehire-track-applications/github.svg)](https://agentmods.dev/skills/strelov1/freehire-cli/freehire-track-applications)
Your own site
<a href="https://agentmods.dev/skills/strelov1/freehire-cli/freehire-track-applications"><img src="https://agentmods.dev/badge/skills/strelov1/freehire-cli/freehire-track-applications/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 freehire-track-applications

Your own site · 80×15
<a href="https://agentmods.dev/skills/strelov1/freehire-cli/freehire-track-applications"><img src="https://agentmods.dev/badge/skills/strelov1/freehire-cli/freehire-track-applications.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 653 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 $0.00081 $0.00653
Opus 5 $0.00041 $0.00327
Sonnet 5 $0.00016 $0.00131
Haiku 4.5 $0.00008 $0.00065

Measured 11d ago against content hash 0bb136211e8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

freehire-track-applications 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 11d 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.

skills/freehire-track-applications/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tracking applications on freehire

Needs a key: freehire auth login --token fhk_… (or FREEHIRE_TOKEN). Every command takes --json. To find the jobs in the first place, use the freehire-job-search skill; every command here takes the same <slug>.

Mark, stage, review

freehire apply <slug>                    # mark applied
freehire save <slug> / unsave <slug>     # bookmark
freehire stage <slug> <stage>            # applied…offer, or rejected/withdrawn
freehire note <slug> a quick reminder    # free-text note (trailing args; no quotes needed)
freehire my --filter applied             # tracked jobs with stage + note (all|viewed|saved|applied)

apply and save are idempotent, so retries are safe. The API owns the stage vocabulary — the CLI only lists it in help, it does not validate client-side, so a rejected stage name is the server telling you the truth.

my is the answer to "where am I with everything": it carries each job's stage and note. A posting that has since been pruned from the catalogue shows as a dash rather than a blank row.

A posting that never answered

If the person applied and was never answered, file it — that is the only channel that gets human evidence into the "possibly inactive" signal other people read:

freehire ghost report <slug> --applied-on 2026-06-01   # the day THEY applied
freehire ghost retract <slug>                          # withdraw it

--applied-on is required and never guessed: ask the person, or take it from freehire my --filter applied. The date is the substance of the claim — it decides when the silence has matured (roughly three weeks) — so a date they did not state is a claim they did not make.

The rest is the server's: it needs a verified email address (403 otherwise), refuses a future date or one older than a year (400), a closed posting or a second report on the same job (409), and caps how many you can file in a day (429). One report is one of four checks; the stronger wording needs a second person, which is also why a report is never displayed as coming from one identifiable applicant.

Read the full file on GitHub · 54 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. 11d ago First seen · 54 lines · 81 tokens per session scan A 0bb136211e8e

Subscribe to this mod's changes

freehire-track-applications is a skill published in the GitHub repository strelov1/freehire-cli (5 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 653 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.