jobs: Instructions file for Codex

AGENTS.md

jobs AGENTS.md is an instructions file for Codex, OpenCode from bensyverson/jobs. It costs 4,904 tokens per session, scanned A, original, MIT.

Project instructions for Jobs, a command-line task manager that stores task changes in SQLite, a small embedded database, and also provides a web dashboard.

In plain words
What is it for?
Use them when modifying Jobs, its CLI, dashboard, database migrations, tests, build process, or documentation.
Why use it?
They show where the core product lives, how to update documentation, and which commands and rules to follow when changing it.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bensyverson/jobs/agents-md"><img src="https://agentmods.dev/badge/instructions/bensyverson/jobs/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,904 This file is loaded in full into every session.
When invoked 4,904 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 $0.04904 $0.04904
Opus 5.5 $0.01962 $0.01962
Sonnet 5.5 $0.00981 $0.00981
Haiku 4.5 $0.00490 $0.00490

Measured today against content hash c303e10f0c6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jobs 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 today.

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 · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT: As you implement features, keep the documentation up to date; update README.md only when a doc file is added or new users must know.

Overview

You are working on Jobs, a hierarchical task manager for the CLI, backed by an event store in SQLite.

Documentation

  • docs/content/docs/ — the published documentation site (Hugo); make docs serves it locally. reference/ is the full CLI reference — the fastest way to learn what a command does.
  • README.md — what Jobs is and a quick start, written for humans
  • DESIGN.md — the dashboard's design system: tokens, type scale, component specs
  • project/ — dated design documents and agent-feedback reports; project/gotchas.md holds project traps and rule feedback
  • Makefile — build, install, test, test-js, and the docs targets
  • scripts/ — re-runnable tooling (screenshots, snapshot replay, getting-started verification)

Architecture

internal/job is the product — the SQLite event store, the plan grammar, and the rendering. cmd/job is a thin cobra CLI over it, and internal/web is a server-rendered dashboard over the same core.

  • Schema changes are numbered migrations in internal/migrations/. They are applied when the database is opened, so any job invocation migrates — there is no server to restart.
  • DESIGN.md is the design system the web rules below defer to, authoritative for everything under internal/web/ — including its desktop-first density target, which outranks the web rules' mobile-first default. The dashboard is localhost-only and read-only, so the rule about public-page <head> metadata does not apply here.
  • The dashboard's JS is mostly plain progressive-enhancement modules in internal/web/assets/js/, not custom elements; only peek-sheet and live-region are registered, and neither uses a shadow root. The web rules' one-element-per-file-with-a-shadow-root convention governs new components — don't retrofit the existing scripts to it as a side quest.
  • This repo builds job. The job on your PATH and the ./job at the repo root are both stale until make install / make build, so a CLI change you just wrote is not exercised by running job until you rebuild.
  • Never name a client or a client's repo in anything committed — code, comments, project/ docs, commit messages, and job titles, descriptions, notes and criteria (the .jobs/log is committed too). Say "a client repo" or "a client store". Real stores from other repos are fine to measure against; their names stay out of this one.

Read the full file on GitHub · 165 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. today Changed · +2 lines · +164 tokens per session c303e10f0c6e
  2. 12d ago Changed · +8 lines · +239 tokens per session 5062337b6c05
  3. 1mo ago Changed · -11 lines · +40 tokens per session 2be19d89e728
  4. 2mo ago First seen · 166 lines · 4,461 tokens per session scan A 41b3a4545cf1

Subscribe to this mod's changes

jobs AGENTS.md is an instructions file published in the GitHub repository bensyverson/jobs (29 stars, last pushed yesterday), licensed MIT. It adds 4,904 tokens to every session, about $0.0196 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.

Related

jobs AGENTS.md compared with instructions from other repositories

jobs AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
jobs AGENTS.mdbensyverson/jobsInstructions file29yesterdayMITA4,904Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode