Borrowing it
Nothing to install: this file belongs to zycdev/codex-long-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.
curl -O https://raw.githubusercontent.com/zycdev/codex-long-jobs/main/AGENTS.mdgit clone --depth 1 https://github.com/zycdev/codex-long-jobsWrote 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.
[](https://agentmods.dev/instructions/zycdev/codex-long-jobs/agents-md)<a href="https://agentmods.dev/instructions/zycdev/codex-long-jobs/agents-md"><img src="https://agentmods.dev/badge/instructions/zycdev/codex-long-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.
<a href="https://agentmods.dev/instructions/zycdev/codex-long-jobs/agents-md"><img src="https://agentmods.dev/badge/instructions/zycdev/codex-long-jobs/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00667 | $0.00667 |
| Opus 5.5 | $0.00267 | $0.00267 |
| Sonnet 5.5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
codex-long-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 29d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
The runtime is scripts/codex_long_jobs.py; scripts/codex-long-jobs is the
shell entrypoint. Skill metadata is in SKILL.md and agents/openai.yaml;
contracts and release evidence are in references/. unittest tests live in
tests/; fake_tmux.py simulates TUI behavior. Releases update CHANGELOG.md
and VERSION.
Build, Test, and Development Commands
There is no build step. Use:
scripts/smoke_test.sh: integration suite.scripts/coverage_test.sh: subprocess-aware branch coverage.scripts/stress_test.sh 10: repeated lifecycle and race tests.ruff check scripts/*.py testsandruff format --check scripts/*.py tests: lint and format checks.shellcheck scripts/codex-long-jobs scripts/*.sh: shell lint.scripts/codex-long-jobs doctor: runtime and TUI diagnostics.
Run the OpenAI Skill validator against the repository root before release.
Architecture & Agent-Specific Invariants
Preserve the established contract: supervisor, worker, and command run outside tmux; tmux is only a disposable viewer and validated live-TUI transport. Completion is event-driven for the model. Local readiness checks are allowed, but never add periodic LLM/model polling.
Durable state is truth; TUI delivery is best effort because Codex has no stable
public wake API. Never inject job output, paste into a busy turn, or submit over
a nonempty composer. Cancellation is explicit and process-group scoped. If no
signal takes effect before natural completion, the actual result wins. Keep
status --json as the result interface; do not add redundant result or reuse
immutable job names.
Coding Style & Naming Conventions
Target Python 3.10+, four-space indentation, type annotations, and 88-character
lines. Follow ruff.toml; use snake_case, test_<behavior>, and unique job
names such as train-model-run-01. Keep runtime dependencies at zero, preserve
argv boundaries, and avoid dash-based sentence breaks in prose.
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.
- 29d ago First seen · 63 lines · 667 tokens per session scan A 47e64be81623
codex-long-jobs AGENTS.md is an instructions file published in the GitHub repository zycdev/codex-long-jobs (3 stars, last pushed 20d ago), licensed MIT. It adds 667 tokens to every session, about $0.0027 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 2026-09-21.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.