search

search is a skill for Claude Code from Mahashwetha/Job-search-email-system-claude. It costs 95 tokens per session (727 once invoked), scanned A, original, MIT.

A tool for looking up companies and job links in an Excel application tracker. It checks both active and rejected or closed applications, including links stored inside Excel hyperlink formulas.

In plain words
What is it for?
Use it to check a job URL, find all roles associated with a company, or confirm that a company or application is not in the tracker.
Why use it?
It answers whether a job or company is already recorded without requiring a manual spreadsheet search. If a URL is not found, it can inspect the page title and try to identify the company.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to check a job URL, find all roles associated with a company, or confirm that a company or application is not in the tracker.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mahashwetha/job-search-email-system-claude/search
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 Mahashwetha/Job-search-email-system-claude --skill search
Clone the repo
git clone --depth 1 https://github.com/Mahashwetha/Job-search-email-system-claude

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 search

README.md
[![agentmods](https://agentmods.dev/badge/skills/mahashwetha/job-search-email-system-claude/search/github.svg)](https://agentmods.dev/skills/mahashwetha/job-search-email-system-claude/search)
Your own site
<a href="https://agentmods.dev/skills/mahashwetha/job-search-email-system-claude/search"><img src="https://agentmods.dev/badge/skills/mahashwetha/job-search-email-system-claude/search/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 search

Your own site · 80×15
<a href="https://agentmods.dev/skills/mahashwetha/job-search-email-system-claude/search"><img src="https://agentmods.dev/badge/skills/mahashwetha/job-search-email-system-claude/search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 727 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 $0.00095 $0.00727
Opus 5 $0.00048 $0.00364
Sonnet 5 $0.00019 $0.00145
Haiku 4.5 $0.00010 $0.00073

Measured 12d ago against content hash 44758102efdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

search 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 12d 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.

.claude/skills/search/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search Tracker

Look up a company or URL across both sheets of List.xlsx (Sheet1 = active applications, Rejected = rejected/closed applications).

What to do based on input

User gives a URL

  1. Open List.xlsx with openpyxl (use temp copy if PermissionError).
  2. Search column C in both sheets for that URL (exact or substring match). Also handle cells with =HYPERLINK(...) formula — extract the URL from inside the formula.
  3. If found → show all matching rows (see Output Format below).
  4. If not found → use requests to fetch the page and extract the <title> tag. Parse the company name from the title (format is usually "Job Title - Company | Platform"). Then search column A in both sheets by that company name.
  5. Report clearly: "Not in tracker" if nothing matches after both attempts.

User gives a company name only

  1. Open List.xlsx with openpyxl (use temp copy if PermissionError).
  2. Search column A in both sheets — case-insensitive substring match.
  3. Show all matching rows across both sheets (see Output Format below).
  4. Report "Not in tracker" if nothing found.

Output Format

Group results by sheet, show row number, company, role, status (with emoji), URL, and any comments:

Found 3 match(es) for "Theodo":

  [Sheet1]
    Row 45 — Theodo | AI Engineer | ✅ Applied
             URL: https://welcometothejungle.com/...
    Row 67 — Theodo | Tech Lead | 🕐 In Progress
             URL: https://...

  [Rejected]
    Row 12 — Theodo | Backend Engineer | ❌ Rejected
             Note: French required

Status emoji mapping:

  • done / applied → ✅ Applied
  • in progress / under review → 🕐 In Progress
  • rejected → ❌ Rejected
  • not available / nothing to apply → ⏸️ No Jobs Available
  • empty / other → ⬜ Not Contacted

Always show the Comments column (col F) if it has content — it often has useful notes like "Job posting CLOSED" or "French required".

Rules

  • Always search BOTH sheets — Sheet1 and Rejected.
  • Skip header row (row 1) when iterating.
  • Company match is case-insensitive substring both ways: query in company OR company in query. Skip empty cells — empty string always matches any substring check, so guard with if company and if url before comparing.
  • For URL search, also check if the URL is wrapped in a HYPERLINK formula.
  • If the user gave a URL that's not in the tracker, always attempt to identify the company from the page before saying "not found".

Read the full file on GitHub · 58 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. 12d ago First seen · 58 lines · 95 tokens per session scan A 44758102efdc

Subscribe to this mod's changes

search is a skill published in the GitHub repository Mahashwetha/Job-search-email-system-claude (9 stars, last pushed 12d ago), licensed MIT. It adds 95 tokens to every session and 727 once invoked, about $0.0005 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.