software_development_department AGENTS.md

software_development_department AGENTS.md is an instructions file for Codex, OpenCode from tranhieutt/software_development_department. It costs 1,412 tokens per session, scanned F, original, MIT.

A repository instruction file that adapts a Claude-based software-development process for Codex. It documents required review gates, the six development phases, safety rules, and commands that must not be run.

In plain words
What is it for?
Use it to guide work through definition, planning, building, verification, review, and release while keeping Claude runtime files unchanged.
Why use it?
It gives coding agents project-specific rules before they answer or change code. This helps preserve the repository's existing workflow and safety boundaries.

Instructions file for CodexOpenCode

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/tranhieutt/software_development_department/agents-md
Clone the repo
git clone --depth 1 https://github.com/tranhieutt/software_development_department

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 software_development_department AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tranhieutt/software_development_department/agents-md.svg)](https://agentmods.dev/instructions/tranhieutt/software_development_department/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tranhieutt/software_development_department/agents-md"><img src="https://agentmods.dev/badge/instructions/tranhieutt/software_development_department/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,412 This file is loaded in full into every session.
When invoked 1,412 The same file — it is already loaded in full.
Security scan F 5 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 $0.01412 $0.01412
Opus 5 $0.00706 $0.00706
Sonnet 5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured yesterday against content hash ba238347edfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

software_development_department AGENTS.md scanned grade F with 5 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- `chmod 777`

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- Reading `~/.docker/config.json`, `~/.kube/config`

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- `curl * | sh`, `curl * | bash`

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- `rm -rf /`, `rm -rf .`, `rm -rf /*`, `rm -rf ./*`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl * | sh`, `curl * | bash`
AGENTS.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD for Codex

This repository is the Software Development Department (SDD) harness.

The canonical source of truth remains Claude-native:

  • CLAUDE.md
  • .claude/settings.json
  • .claude/agents/
  • .claude/skills/
  • .claude/hooks/
  • .claude/memory/

Codex support is an adapter layer. Do not change Claude runtime behavior to make Codex work.

Operating Rule

Before any non-trivial software-development response, review:

  1. .claude/skills/using-sdd/SKILL.md
  2. docs/technical/SDD_LIFECYCLE_MAP.md
  3. The specific SDD skill that matches the task

Use SDD's six-phase map:

DEFINE -> PLAN -> BUILD -> VERIFY -> REVIEW -> SHIP

For implementation work, state the pre-code gate before the first production edit:

Pre-code gate: <Fast|Spec|Plan|Interview|Override> satisfied by <evidence>; next edit: <file>; verification: <command/check>.

Codex Runtime Notes

Claude Code hooks in .claude/settings.json do not run automatically in Codex. Codex must manually honor the same gates through instructions, file inspection, and verification commands.

Preserve these boundaries:

  • Do not move or rename .claude/skills.
  • Do not move or rename .claude/agents.
  • Do not weaken .claude/settings.json permissions.
  • Do not replace Claude hooks with Codex-specific behavior.
  • Do not claim work is done without fresh evidence.
  • Do not commit or push unless the user explicitly asks.

Safety Rules (Manual Deny List)

Claude Code enforces these rules automatically through hooks and permissions. Codex does not run those hooks, so you must enforce these rules manually.

Blocked Commands — NEVER Execute

These commands are forbidden. If a task seems to require one, stop and ask the user for explicit approval and an alternative approach.

Destructive filesystem:

  • rm -rf /, rm -rf ., rm -rf /*, rm -rf ./*
  • mkfs, dd if=/dev/zero, dd if=/dev/null
  • chmod 777

Credential and secret exposure:

  • Reading .env, .env.*, or any *.env file
  • Reading ~/.ssh/, ~/.aws/, ~/.azure/, ~/.gnupg/, ~/.config/gcloud/
  • Reading ~/.docker/config.json, ~/.kube/config
  • Writing to .env, .env.*, .bashrc, .zshrc, .profile
  • cat .env, type .env, or any command that outputs secret files

Read the full file on GitHub · 174 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. yesterday First seen · 174 lines · 1,412 tokens per session scan F ba238347edfd

Subscribe to this mod's changes

software_development_department AGENTS.md is an instructions file published in the GitHub repository tranhieutt/software_development_department (71 stars, last pushed 3mo ago), licensed MIT. It adds 1,412 tokens to every session, about $0.0071 per session on Opus 5. A static security scan graded it F with 5 findings (asks for root, reaches for credential files, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.