A workflow for reviewing job-application updates from Gmail, LinkedIn, and other platforms. It summarizes updates by priority, prepares reply drafts, checks them with you, and sends approved replies.

Checking for new application updates, deciding which need attention, drafting responses, and following the user’s rules for follow-ups and outreach.

It brings application messages into one review process so important updates are easier to find and respond to. It also applies stored job-search and communication preferences during the review.

How galiprandi/job-seeker configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to galiprandi/job-seeker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/galiprandi/job-seeker/main/.agents/skills/news/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/galiprandi/job-seeker

Made for: Claude Code, Codex.

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/galiprandi/job-seeker/news/github.svg)](https://agentmods.dev/skills/galiprandi/job-seeker/news)

Your own site

<a href="https://agentmods.dev/skills/galiprandi/job-seeker/news"><img src="https://agentmods.dev/badge/skills/galiprandi/job-seeker/news/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/galiprandi/job-seeker/news"><img src="https://agentmods.dev/badge/skills/galiprandi/job-seeker/news.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,696 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 136
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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	$0.00032	$0.07696
Opus 5.5	$0.00013	$0.03078
Sonnet 5.5	$0.00006	$0.01539
Haiku 4.5	$0.00003	$0.00770

Measured 2d ago against content hash c5b0cf5eea48, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

news 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 2d 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/news/SKILL.md · 521 lines

How it starts

The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.

News

Trigger

Keyword: news

The user says news (or variants: "updates", "check", "any updates") and the full review routine is automatically triggered. No further instructions needed — the agent executes the entire flow from start to finish.

Also runs in parallel when the user launches an application.

Flow

0. Pre-flight

Verify active LinkedIn and Gmail sessions. If session closed → open browser with wrapper (see AGENTS.md "Browser session"): node .agents/skills/browser-automation/scripts/browser.js open <url> --headed (Gold Rule 5) → notify user → wait for confirmation
Browser: always use node .agents/skills/browser-automation/scripts/browser.js for open/close/goto. See AGENTS.md "Browser session" for details. Never call agent-browser open directly, never open Chrome directly

Load active preferences (see memory skill):

node scripts/db.js "SELECT category, key, value, confidence, source FROM preferences WHERE user_id = <user_id> AND status = 'active' ORDER BY category, key"

Load strategy (see AGENTS.md "Strategy levels"):
```
node scripts/db.js "SELECT data->'strategy' AS strategy FROM users WHERE id = <user_id>"
```
Respect: follow_up_days (days before sending follow-up), cold_outreach (whether to send cold messages to recruiters). If news not in sources_active, warn the user

1. Collect updates (in parallel)

Parallelization strategy: when subagents are available, dispatch background subagents (subagent_general) per source to collect updates simultaneously. Each subagent returns a structured list of items (sender, subject, snippet, category guess, action items, scheduling links if any). The main agent then merges and classifies. If subagents are not available (e.g: single-session constraint), fall back to sequential collection.

Subagent dispatch pattern:

┌─────────────────────────────────────────────────────┐
│  Main agent (orchestrator)                          │
│  - Loads preferences, strategy, availability        │
│  - Dispatches subagents in parallel                 │
│  - Merges results, classifies, presents summary     │
├─────────────────────────────────────────────────────┤
│  Subagent A (Gmail)     Subagent B (LinkedIn)       │
│  - Inbox unread         - Messages unread           │
│  - Job Alerts folder    - Notifications             │
│  - Extract sched links  - Saved Jobs                │
│  - Returns JSON list    - Returns JSON list         │
├─────────────────────────────────────────────────────┤
│  Subagent C (DB)        Subagent D (Sched links)    │
│  - Pending follow-ups   - Opens each Calendly/SR   │
│  - Pipeline stages      - Filters by availability   │
│  - Returns JSON list    - Returns slot table        │
└─────────────────────────────────────────────────────┘

Read the full file on GitHub · 521 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.

2d ago Changed c5b0cf5eea48
1mo ago Changed 0aec54653235
1mo ago First seen · 521 lines · 32 tokens per session scan A 05b27ae1579c

Subscribe to this mod's changes

news is a skill published in the GitHub repository galiprandi/job-seeker (58 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 7,696 once invoked, about $0.0001 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 2026-08-30.

Claude Code Productivity ai-agents automation career job-search linkedin

interviewing

Use when the user gets an interview invitation, moves into an interview process, wants to track interview stages, capture post-interview notes, draft follow-up messages, or update an application to interviewing.

Remotivated/job-hunt-skills · 43 tokens

career-compass

Use for any job-search or career task, even a short casual ask that never names Career Compass. Triggers include a pasted job posting or JD, a résumé or CV, "should I apply", "do I fit this", "help me apply", tailoring a résumé or cover letter, a LinkedIn headline or About section, tracking applications, a recruiter…

benskamps/career-compass-mcp · 211 tokens

vitaecontext-build

Build, normalize, and maintain the user's Career Context file so downstream platform outputs stay factual and consistent. Use when the user wants an agent to consolidate CV data, LinkedIn exports, GitHub history, project summaries, bio facts, achievements, or positioning into one professional source of truth before…

vitaecontext/vitaecontext · 67 tokens

get-started

Use when the user is new to Job Hunt Skills and wants to see what it does or set up their workspace — including "I'm new to Job Hunt Skills", "help me get started", "set me up", "first time using this", "here's my resume, tailor it for this job", "can you look at my resume", pasting a resume and a job posting…

Remotivated/job-hunt-skills · 132 tokens

today

See what needs attention in your job search today, such as follow-ups due, upcoming interviews, and stale applications, in priority order.

benskamps/career-compass-mcp · 29 tokens

week

Review your job-search week. What moved, stalled or closed, the patterns in your notes, your pace against your goal, and one focus for next week.

benskamps/career-compass-mcp · 34 tokens

job-seeker: Skill for Claude Code