open-jobs: Instructions file for Codex

AGENTS.md

open-jobs AGENTS.md is an instructions file for Codex, OpenCode from elliottdehn/open-jobs. It costs 5,687 tokens per session, scanned A, original, CC0-1.0.

Instructions for using a local database of about two million current job postings to find suitable work. The records include job descriptions and searchable details, while extra fields such as seniority, role, work arrangement, and skills can be added through enrichment.

In plain words
What is it for?
Searching job postings by meaning, filtering by location or salary, enriching selected results, and improving the tools used to browse and match jobs.
Why use it?
It avoids downloading and searching the entire dataset yourself. Semantic search helps find postings related to an ideal job description, while salary information is extracted from the job text.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

This is elliottdehn/open-jobs's own configuration. It tells Codex and OpenCode how to work on open-jobs 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 open-jobs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to elliottdehn/open-jobs. 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/elliottdehn/open-jobs/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/elliottdehn/open-jobs

Made for: Codex, OpenCode.

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 open-jobs AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/elliottdehn/open-jobs/agents-md/github.svg)](https://agentmods.dev/instructions/elliottdehn/open-jobs/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/elliottdehn/open-jobs/agents-md"><img src="https://agentmods.dev/badge/instructions/elliottdehn/open-jobs/agents-md/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 open-jobs AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/elliottdehn/open-jobs/agents-md"><img src="https://agentmods.dev/badge/instructions/elliottdehn/open-jobs/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,687 This file is loaded in full into every session.
When invoked 5,687 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.05687 $0.05687
Opus 5 $0.02844 $0.02844
Sonnet 5 $0.01137 $0.01137
Haiku 4.5 $0.00569 $0.00569

Measured yesterday against content hash 38f237b72386, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

open-jobs AGENTS.md scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`.claude/settings.json` already *allows* the one `curl` command that posts to the relay, so posts
AGENTS.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

open-jobs: agent workflow

You are helping a person find a job using a local slice of ~2M current job postings. Everything runs on this machine except one call that embeds their ideal job description. Work in work/.

The story (tell it if asked, keep it short)

The original open-jobs repository was lost in a data-loss event. The dataset was rebuilt from scratch with a similar approach, better and stronger: a daily crawl of ~65,000 company boards (~2M open jobs) with full descriptions, an embedding of every posting, and semantic slicing so nobody has to download all of it. Jobs are not enriched by default: the raw record is title, company, location, URL, dates, description text and vector. Structured fields (seniority, role family, work arrangement, skills, company profile…) come from enrich (metered, cached), and salary is also extracted mechanically from the description text at compile time (tools/salary.py: stated ranges/figures with currency and period, annualized) so the salary facet works without any LLM.

This code is meant to be changed

Nothing here is ossified. tools/jobs.py, tools/search.html, tools/locparse.py, tools/salary.py are small, dependency-light, and written to be edited for the person in front of you: add a facet they care about, change how the pre-ranking is weighted, tweak the salary or location parsing when it misreads their market, write a different search page altogether, pull a bigger or smaller slice, bolt on a DuckDB query. If the person asks for something the tools don't do, change the tools rather than working around them, and keep the change in their clone. The only fixed contracts are the data (work/jobs.parquet columns, the group file shape) and the public endpoints (/embed, /data/*, /enrich).

0. Setup (once)

  • Needs uv (https://docs.astral.sh/uv/) and Python 3.10+. All commands are uv run tools/jobs.py <cmd>.
  • WORKER_URL defaults to the public index (https://backend.dehnbostele.workers.dev); DATA_URL can point group/manifest downloads at a local mirror.
  • uv run tools/jobs.py status shows what exists in work/.

Read the full file on GitHub · 307 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. yesterday Changed · +42 lines · +830 tokens per session 38f237b72386
  2. 2d ago Changed · +12 lines · +238 tokens per session b37f3f712fb4
  3. 3d ago Changed · +6 lines · +123 tokens per session 1d42d9f57d99
  4. 6d ago Changed · +32 lines · +644 tokens per session 9d33856ca60c
  5. 10d ago First seen · 215 lines · 3,852 tokens per session scan A 3223d9da44bc

Subscribe to this mod's changes

open-jobs AGENTS.md is an instructions file published in the GitHub repository elliottdehn/open-jobs (281 stars, last pushed today), licensed CC0-1.0. It adds 5,687 tokens to every session, about $0.0284 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens