agentmods.dev

Codex-Engineering-Workflow-Pack AGENTS.md

Contributor instructions for a local-first engineering toolkit for Codex, covering supervision, governance, isolated workspaces, controlled task dispatch, and parallel agent workflows. It defines which system is authoritative for ownership, scope, checks, budgets, review, and finalization.

In plain words
What is it for?
Use it when contributing to the toolkit, choosing an execution owner, managing worktrees, coordinating agents, reviewing changes, and running the project's required tests and checks.
Why use it?
It keeps work organized and prevents multiple agents or systems from changing the same task workspace. It also preserves required checks and avoids expanding provider support or weakening safeguards during ordinary feature work.

Instructions file for CodexOpenCode

1 yesterday A scan 218 tokens original MIT
View the source file SetraTheXX/Codex-Engineering-Workflow-Pack
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/setrathexx/codex-engineering-workflow-pack/agents-md
Clone the repo
git clone --depth 1 https://github.com/SetraTheXX/Codex-Engineering-Workflow-Pack

Made for: Codex, OpenCode.

Per session 218 This file is loaded in full into every session.
When invoked 218 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00218 $0.00218
Opus 5 $0.00109 $0.00109
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash 861d94fa4156, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Codex-Engineering-Workflow-Pack 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 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.

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 · 10 lines

What it actually says

CEWP Contributor Instructions

  • Preserve CEWP as a Codex-first supervision, governance, and evidence layer. Native Codex is the simpler choice for low-risk one-step work.
  • Keep provider expansion paused through 1.0. OpenCode is experimental and maintenance-only; do not add Claude, Gemini, Hermes, or automatic model routing.
  • Treat CEWP Core as authoritative for ownership, scope, policy, verification, budgets, reviewer PASS, and finalization. Hooks and UI output are projections only.
  • Use one execution owner (managed, native, or audit-only) and one managed backend per checkpoint. Never let host and child execution mutate the same task worktree.
  • Keep changes narrow, local-first, and dependency-free unless a dependency has a demonstrated contract-level benefit.
  • Run focused contracts while editing, then npm test, npm run check, npm run pack:dry-run, and git diff --check before completion.
  • Do not publish, tag, release, or weaken a non-waivable gate as part of ordinary feature work.
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 First seen · 10 lines · 218 tokens per session scan A 861d94fa4156

Subscribe to this mod's changes

Codex-Engineering-Workflow-Pack AGENTS.md is an instructions file published in the GitHub repository SetraTheXX/Codex-Engineering-Workflow-Pack (1 stars, last pushed yesterday), licensed MIT. It adds 218 tokens to every session, about $0.0011 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.

Code reviewGit and workflowTestingagentic-workflowai-codingcodexcodex-skillsdeveloper-toolworkflow
Related

Other instructions, from other repositories

cctop AGENTS.md

Instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.

st0012/cctop · 2,107 tokens

cctop CLAUDE.md

Instructions for st0012/cctop: This repository keeps shared agent instructions in AGENTS.md. Read AGENTS.md now and follow it as the source of truth for cctop development.

st0012/cctop · 40 tokens

frappe-agent AGENTS.md

Instructions for Dkm0315/frappe-agent, covering frappe agent instructions, core behavior, bench guidance, app provenance and erpnext guidance.

Dkm0315/frappe-agent · 577 tokens

frappe-agent copilot-instructions.md

Instructions for Dkm0315/frappe-agent: Treat this repository as Frappe, ERPNext, and Frappe ecosystem guidance for coding agents.

Dkm0315/frappe-agent · 286 tokens

frappe-agent CLAUDE.md

Instructions for Dkm0315/frappe-agent: This repository contains Codex-native plugin assets plus portable Frappe, ERPNext, and Frappe ecosystem development guidance.

Dkm0315/frappe-agent · 318 tokens

agent-skills AGENTS.md

Instructions for sayeed1999/agent-skills, covering agents.md, output style, output style, 1. think before code and 2. simplicity.

sayeed1999/agent-skills · 1,146 tokens