What is openhire-job-search?

A local workflow for evaluating job postings and tailoring application materials with OpenHire data. The user's CV and personal details stay in local files rather than being sent to the job-search service.

Use it to assess a posting, adapt a CV from the user's source CV, build STAR interview stories, or draft a short outreach note.

It separates private application information from public or employer-provided posting data. This reduces the risk of exposing a name, contact details, or CV to an external tool.

openhire-job-search — Skill for Claude Code by gzchenhao/openhire

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 gzchenhao/openhire --skill openhire-job-search

Clone the repo

git clone --depth 1 https://github.com/gzchenhao/openhire

Made for: Claude Code.

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

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/gzchenhao/openhire/openhire-job-search/github.svg)](https://agentmods.dev/skills/gzchenhao/openhire/openhire-job-search)

Your own site

<a href="https://agentmods.dev/skills/gzchenhao/openhire/openhire-job-search"><img src="https://agentmods.dev/badge/skills/gzchenhao/openhire/openhire-job-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.

Your own site · 80×15

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

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,012 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	$0.00080	$0.01012
Opus 5.5	$0.00032	$0.00405
Sonnet 5.5	$0.00016	$0.00202
Haiku 4.5	$0.00008	$0.00101

Measured 6d ago against content hash ab126c0c66c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openhire-job-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 6d 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/openhire-job-search/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenHire job search (local workflow)

OpenHire supplies facts about postings from employers' own hiring systems: whether a posting is still live, how long it has been open, the degree and years it asks for, and whether the company is publishing more or fewer postings lately. Everything about the user stays on this machine. You (the assistant) do the reading and writing locally.

The one rule that never bends

Never pass the CV, its text, the user's name, email, phone, address or any file to an OpenHire tool. Tools take only a job_id, a company name, search filters, or an anonymous fingerprint. If a step seems to need the CV on the server, it does not: do it here, on this machine.

Files (in the folder the user is working in)

File	What it is	Who writes it
`cv.md`	The user's real CV. Source of truth.	The user. You never invent anything in it.
`openhire/evaluations.md`	One section per posting evaluated.	You.
`openhire/cv-<job_id>.md`	A CV reworded for one posting.	You, from `cv.md` only.
`openhire/stories.md`	STAR + reflection stories mined from `cv.md` and what the user tells you.	You.
`openhire/outreach.md`	Short notes the user may send themselves.	You. The user sends them, never you.

If cv.md does not exist, ask the user to put their CV there (Markdown or pasted text). Do not upload it anywhere to read it.

Modes

1. Evaluate a posting ("评估这个岗位", "how well do I fit")

Get the facts: search_jobs (by company and title) to find the row, then read its dates_in_words, check_before_apply, requirements and apply_channel; get_company_info for hiring_trend; optionally check_employer with the job_id.
Compare with cv.md here: list which stated requirements the CV shows evidence for, which it does not, and what is only "preferred".
Write a section to openhire/evaluations.md with three parts: Facts from the employer's system (quote the sentences), Fit against my CV (met / not shown / preferred only), Questions to ask before applying.
Do not give a pass/fail verdict or a single score that says "do not apply". Never call a posting fake, a ghost or 僵尸岗: a long time open is a measured fact, not evidence. The user decides.

Read the full file on GitHub · 53 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.

6d ago First seen · 53 lines · 80 tokens per session scan A ab126c0c66c3

Subscribe to this mod's changes

openhire-job-search is a skill published in the GitHub repository gzchenhao/openhire (14 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,012 once invoked, about $0.0003 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 2026-10-31.

Productivity ai-agents ashby ats claude cursor greenhouse

openhire-job-search next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
openhire-job-searchgzchenhao/openhire	Skill	14	yesterday	MIT	A	80	Claude Code
job-triageAkbarDevop/ai-job-agent	Skill	68	6mo ago	MIT	A	98	Claude Code
job-applyAkbarDevop/ai-job-agent	Skill	68	6mo ago	MIT	A	138	Claude Code
job-dashboardAkbarDevop/ai-job-agent	Skill	68	6mo ago	MIT	A	127	Claude Code
job-statusAkbarDevop/ai-job-agent	Skill	68	6mo ago	MIT	A	134	Claude Code
job-trackAkbarDevop/ai-job-agent	Skill	68	6mo ago	MIT	A	103	Claude Code
job-recapAkbarDevop/ai-job-agent	Skill	68	6mo ago	MIT	A	177	Claude Code