agentmods.dev

ai-job-search: Command for Claude Code

.claude/commands/search.md

search is a command for Claude Code from suraj-davariya/ai-job-search. It costs 30 tokens per session (470 once invoked), scanned A, original, MIT.

A job-search command that checks the job websites you configure for recent openings, removes duplicates, and ranks matches by fit.

In plain words
What is it for?
Use it to find new roles, narrow results by category, location, or focus area, review the best matches, and send selected postings to the application workflow.
Why use it?
It reduces the work of checking several job portals and prevents the same posting from appearing repeatedly. It also keeps track of jobs you have already seen.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

This is suraj-davariya/ai-job-search's own configuration. It tells Claude Code how to work on ai-job-search itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-job-search configures →

not rated 24repo +1 4mo ago A scan 30 tokens original MIT
View source ↗ suraj-davariya/ai-job-search suraj-davariya.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to suraj-davariya/ai-job-search. 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/suraj-davariya/ai-job-search/main/.claude/commands/search.md
Clone the repo
git clone --depth 1 https://github.com/suraj-davariya/ai-job-search

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/commands/suraj-davariya/ai-job-search/search/github.svg)](https://agentmods.dev/commands/suraj-davariya/ai-job-search/search)
Your own site
<a href="https://agentmods.dev/commands/suraj-davariya/ai-job-search/search"><img src="https://agentmods.dev/badge/commands/suraj-davariya/ai-job-search/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/commands/suraj-davariya/ai-job-search/search"><img src="https://agentmods.dev/badge/commands/suraj-davariya/ai-job-search/search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 470 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 $0.00030 $0.00470
Opus 5.5 $0.00012 $0.00188
Sonnet 5.5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 2mo ago against content hash 1fb94d65719c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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/commands/search.md · 29 lines

What it actually says

/search — Job Discovery

Canonical command: /search Alias: /scrape Spec: REQ-1001–1012, ADR-0004, DEC-011, DEC-012

Activate the job-scraper skill and run its full workflow:

  1. Load state — read job_scraper/seen_jobs.json, job_search_tracker.csv, and .claude/skills/job-scraper/search-queries.md (REQ-1002).
  2. Select query scope — default: top 3 priority categories; optional focus argument narrows/prioritizes; broad runs all categories (REQ-1001).
  3. Search — issue WebSearch queries from the user's configured portals, query strings, and geography; last 14 days (REQ-1003).
  4. Fetch & parse — pre-filter on snippets, WebFetch promising results; on failure prompt paste (DEC-011) (REQ-1004).
  5. Quick fit — assign High / Medium / Low signal per candidate profile (REQ-1005).
  6. Deduplicate — skip seen URLs and known company+role pairs; record all in seen_jobs.json (REQ-1006).
  7. Filter — apply geo tiers and date rules from search-queries.md (REQ-1010, REQ-1011).
  8. Present — summary header + fit-sorted table; 2–3 why-bullets for High matches; ask for number(s) (REQ-1007).
  9. Hand off — pass chosen job URL or text to /apply; mark status evaluated in seen_jobs.json (REQ-1008).

All portal targeting, geography, and site selections come from the user's search-queries.md — nothing is hardcoded here (DEC-012).

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. 2mo ago First seen · 29 lines · 0 tokens per session scan A 1fb94d65719c

Subscribe to this mod's changes

search is a command published in the GitHub repository suraj-davariya/ai-job-search (24 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 470 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.

Researchagentic-aiai-agentsai-job-applicationsai-job-applyai-job-searchanthropic
Related

search compared with commands from other repositories

search next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
searchsuraj-davariya/ai-job-searchCommand244mo agoMITA30Claude Code
cost-optimizewshobson/agentsCommand42kyesterdayMITA26Claude Code
refactor-cleanwshobson/agentsCommand42kyesterdayMITA26Claude Code
deps-auditwshobson/agentsCommand42kyesterdayMITA23Claude Code
export-closedloop-learningsclosedloop-ai/claude-pluginsCommand123todayApache-2.0A13Claude Code
research-verifydrobins25/craftCommand73yesterdayMITA28Claude Code
spreadsheet-auditintellegix/intellegix-code-agent-toolkitCommand574d agoMITA0Claude Code