jobfindsme: Instructions file for Codex

AGENTS.md

jobfindsme AGENTS.md is an instructions file for Codex, OpenCode from russeell/jobfindsme. It costs 2,682 tokens per session, scanned B, original, MIT.

Repository instructions for jobfindsme, a tool that finds jobs matching a person’s constraints, ranks them, tracks application status, and provides direct application links.

In plain words
What is it for?
Use them when changing jobfindsme, its setup or workflow, its privacy rules, or the tests that check agent behavior.
Why use it?
They keep job matching factual and consistent while preventing already applied jobs from being suggested again.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is russeell/jobfindsme's own configuration. It tells Codex and OpenCode how to work on jobfindsme 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 jobfindsme configures →

Reuse

Borrowing it

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

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 jobfindsme AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/russeell/jobfindsme/agents-md"><img src="https://agentmods.dev/badge/instructions/russeell/jobfindsme/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,682 This file is loaded in full into every session.
When invoked 2,682 The same file — it is already loaded in full.
Security scan B 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 $0.02682 $0.02682
Opus 5 $0.01341 $0.01341
Sonnet 5 $0.00536 $0.00536
Haiku 4.5 $0.00268 $0.00268

Measured 8d ago against content hash 85826cb83066, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

jobfindsme AGENTS.md scanned grade B 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 8d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

Never tell the user to open a raw Chrome instance or invoke `google-chrome`
AGENTS.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

jobfindsme — Agent Instructions

The canonical Agent Skill is skills/jobfindsme/SKILL.md. Codex, Claude, and Cursor adapters must consume that file without host-specific workflow forks. After changing it, run python scripts/sync_skill.py and the Agent behavior tests in evaluation/agent_behavior/data/.

jobfindsme helps users find more qualified jobs across sources with less time, fewer irrelevant results, and minimal setup. The Server hard-filters jobs by user constraints, extracts structured signals, ranks deterministically, and returns bounded facts plus a factual summary; the Agent organizes the final expression and never invents facts. It preserves job and application state and returns inspectable evidence with direct apply links.

The user only cares about three things — keep everything else invisible:

  1. ① 找岗位 — fastest path from a request to matched jobs + apply links.
  2. ② 定时推送 — pushes at the user's exact time and frequency; applied jobs are never re-suggested.
  3. ③ 查历史 — every job ever matched/shown, queryable with its state (applied/saved/rejected) and first-seen time.

Never surface internal concepts (Workspace IDs, cron syntax, raw signals, connector names) to the user unless asked.

The first search establishes a baseline. Later searches should focus on new or materially changed jobs and must not repeat unchanged results merely to fill a list. Never claim that every configured source has equal data or recommendation quality.

First-Time Setup

BOSS直聘 requires account login and maintained live sources currently use a dedicated local Chrome bridge. Do not begin with a technical questionnaire. Proceed with the profile, plan, and search workflow. If diagnostics show that the browser is unavailable or BOSS is logged out, give the user one action: run jobfindsme setup, complete login if requested, keep that process running, and then retry once.

Login state persists, but the local browser bridge must be running during a search.

Read the full file on GitHub · 217 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. 8d ago First seen · 217 lines · 2,682 tokens per session scan B 85826cb83066

Subscribe to this mod's changes

jobfindsme AGENTS.md is an instructions file published in the GitHub repository russeell/jobfindsme (15 stars, last pushed 15d ago), licensed MIT. It adds 2,682 tokens to every session, about $0.0134 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens