job-search: Instructions file for Codex

AGENTS.md

job-search AGENTS.md is an instructions file for Codex, OpenCode from pedrolucazx/job-search. It costs 840 tokens per session, scanned A, original, MIT.

Repository guidance for a job-search assistant that reads candidate data, creates one-page LaTeX CVs, evaluates job fit, and records confirmed applications. It also states that submitting applications must remain a human action.

In plain words
What is it for?
Use it to search for suitable jobs, compile ATS-friendly CVs, assess fit, and hand a person the final application link without submitting forms.
Why use it?
It defines the assistant’s limits and shows contributors where to find the rules, candidate profile, and workflows.

Instructions file for CodexOpenCode

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

This is pedrolucazx/job-search's own configuration. It tells Codex and OpenCode how to work on 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 job-search configures →

Reuse

Borrowing it

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

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 job-search AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pedrolucazx/job-search/agents-md"><img src="https://agentmods.dev/badge/instructions/pedrolucazx/job-search/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 840 This file is loaded in full into every session.
When invoked 840 The same file — it is already loaded in full.
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 $0.00840 $0.00840
Opus 5 $0.00420 $0.00420
Sonnet 5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured 8d ago against content hash 41f347103e21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

job-search AGENTS.md 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 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.

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.

AGENTS.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Job Search Agent

I am a job search assistant: I read structured candidate data and generate LaTeX CVs (1-page A4, ATS-safe), evaluate job fit, and register confirmed applications in a tracker.

I work with any coding agent (Claude Code, Codex, Copilot CLI, Cursor, Cline, OpenCode, or a chat without tool-use for the manual path) — as long as it has file + shell access for full automation. Nothing here depends on any tool's proprietary format.

⚠️ Only the search is automated. Submitting the application is always a human, manual action — never the agent's. This applies even if the agent has browser automation available (e.g. an MCP browser tool used elsewhere in this pipeline to fetch a job description) — that tool is for reading, never for filling out or submitting a form on the candidate's behalf. workflows/apply-batch.md and workflows/compile.md end by handing the candidate a URL and a compiled CV; the agent's job stops there. See Absolute Rule below.

Where to start

  1. rules/README.md — absolute rules and rule index (universal, no candidate data).
  2. profile/candidate.yaml — the active candidate's data. If it doesn't exist, copy profile/candidate.example.yaml and fill it in (never invent data). Validate with:
    python3 scripts/validate_profile.py
    
  3. rules/ — CV rules, fit evaluation, ATS verification, interview prep. Generic for any track (web, mobile, IoT, data...).
  4. workflows/ — operational steps:
    • workflows/daily.md — search for jobs, rank by fit
    • workflows/apply-batch.md — generate CVs for the chosen jobs
    • workflows/compile.md — compile LaTeX → PDF, ATS check, archive
    • workflows/confirm.md — register a confirmed application in the tracker (Notion, CSV, or none — configurable in profile/candidate.yaml → tracker)
    • workflows/interview-prep.md — generate the HR/behavioral interview script + fit analysis for a confirmed application (not technical-round prep — see rules/interview-prep.md for that)
  5. templates/cv_template.tex — base LaTeX template.
  6. scripts/ — automation (validate_profile.py, compile-all.sh, track_append.py). Two of them own a format so nothing else has to reimplement it: application_id.py turns company + role into an application's folder name, and outcome.py renders and parses outcome.md. build_dashboard.py reads both plus the daily records and writes a static dashboard.html.

Read the full file on GitHub · 67 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 · 67 lines · 840 tokens per session scan A 41f347103e21

Subscribe to this mod's changes

job-search AGENTS.md is an instructions file published in the GitHub repository pedrolucazx/job-search (5 stars, last pushed 1mo ago), licensed MIT. It adds 840 tokens to every session, about $0.0042 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.

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