A connector for tracking job applications in jobctl, a web application for managing a job search. It records applications, recruiter contacts, interviews, offers, rejections, and related analysis.

Adding or updating applications, recording recruiter and interview notes, assessing role fit, saving company research, and tracking next steps.

It keeps job-search events and notes in one timeline instead of leaving them scattered across conversations and personal records.

jobctl — Skill for Claude Code by DmytroRybka

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 DmytroRybka/jobctl-claude --skill jobctl

Clone the repo

git clone --depth 1 https://github.com/DmytroRybka/jobctl-claude

Made for: Claude Code.

Or install jobctl, the plugin that ships this one along with the rest of its 1 skill.

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/dmytrorybka/jobctl-claude/jobctl/github.svg)](https://agentmods.dev/skills/dmytrorybka/jobctl-claude/jobctl)

Your own site

<a href="https://agentmods.dev/skills/dmytrorybka/jobctl-claude/jobctl"><img src="https://agentmods.dev/badge/skills/dmytrorybka/jobctl-claude/jobctl/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/dmytrorybka/jobctl-claude/jobctl"><img src="https://agentmods.dev/badge/skills/dmytrorybka/jobctl-claude/jobctl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 780 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	$0.00067	$0.00780
Opus 5	$0.00034	$0.00390
Sonnet 5	$0.00013	$0.00156
Haiku 4.5	$0.00007	$0.00078

Measured 11d ago against content hash dfb9f9258c9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

jobctl 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.

plugins/jobctl/skills/jobctl/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

jobctl — job application tracking

jobctl is the user's job-application tracker. You are the primary writer: whenever the user mentions anything about their job search, record it via the jobctl MCP tools without being asked. The user reads and plans in the dashboard at https://app.jobctl.app.

Core rules

Record immediately. "I applied to Bosch" → add_application (or update_application to applied if the card exists). Don't ask permission for routine tracking; do tell the user what you recorded.
One card per company+role. Before adding, list_applications to check for an existing card; the API also returns duplicates warnings — if present, update the existing card instead.
Keep the timeline honest. Recruiter calls, sent messages, feedback → add_note. Status changes are logged automatically.
Save your analysis — it is product data, not chat.
- Vacancy fit assessment ("why this role fits, gaps, level/salary advice, process notes") → match_notes field (markdown, ≤20 KB) on add/update.
- Company research (business, culture, comp bands, risks, interview process, sources) → attach_analysis (markdown, ≤100 KB, replaces previous).
Always set next_action + next_action_due so the user's "Needs your attention" list stays useful. Clear it when done, set the next one.

Statuses

started_apply → waiting_referral (parked on a referral ask, not yet submitted) → applied → waiting → interview_1 → interview_2 → offer → accepted. Terminal: rejected, no_response, withdrawn, on_hold. archived = old campaigns only (excluded from analytics). Setting applied auto-stamps applied_at with today when empty.

Raw one-liners

add_application({raw: "..."}) parses: "Company, Role, prio A|B|C, due <date>, remote|hybrid|onsite, via <source>, https://…, in <location>, applied <date>". Dates are DD/MM or natural ("friday"). Salaries are integer EUR (e.g. 120000).

Interviews

log_interview with scheduled_at (ISO, timezone!), attendees [{name, url?}] (LinkedIn profiles), links [{label?, url}] (prep material, meeting link), status planned|done, recap after it happened. Max 10 per application. The soonest upcoming one drives the card's next-interview date.

Read the full file on GitHub · 40 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.

11d ago First seen · 40 lines · 67 tokens per session scan A dfb9f9258c9f

Subscribe to this mod's changes

jobctl is a skill published in the GitHub repository DmytroRybka/jobctl-claude (0 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 780 once invoked, about $0.0003 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.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens