Codex Architect

What it does

When your agent uses it

• : designing features
• Evaluating architecture
• Getting second opinion on design

Example prompts

• “/codex-architect”

Requirements

• Pre-approved tools (allowed-tools): Read, Grep, Glob, Agent, Bash(node:*), Write

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Understand the project structure by discovering it: ls at the repository root, then list the directories it actually shows — do not assume…
2. 2Search related modules: grep -rn "keyword" . -l | head -10 — rooted at the repository, or at a directory the discovery step above actually…
3. 3Read existing implementations: cat | head -150
4. 4Understand existing architecture patterns and conventions

What it can do on your machine

Read from SKILL.md and the folder at commit c9a2036. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Grep
  • Glob
  • Agent
  • Bash(node:*)
  • Write

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codex Architect loads about 899 tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 277 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~68

When it runs · the whole SKILL.md, loaded when a task matches

~899

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sd0xdev/sd0x-harness at commit c9a2036, republished under its MIT licence (© sd0xdev). 277 words, ~899 tokens.

name

codex-architect

description

Codex architecture consulting. Use when: designing features, evaluating architecture, getting second opinion on design. Not for: implementation (use codex-implement), code review (use codex-code-review). Output: architecture advice + design recommendations.

allowed-tools

Read, Grep, Glob, Agent, Bash(node:*), Write

/codex-architect "<question>"
/codex-architect "Evaluate this design" --context src/xxx.ts --mode review
/codex-architect "Redis vs MongoDB?" --mode compare

User -> Claude -> Codex -> Integrate
          |         |         |
    Initial thinking  Third perspective  Combined advice

/codex-architect -> /tech-spec -> /review-spec -> /codex-implement -> /codex-review-fast
    Design           Plan          Review          Implement          Code Review

Input: /codex-architect "How to design a high-concurrency cache?"
Action: Codex analysis -> Claude supplement -> Integrated output

Input: /codex-architect "Any issues with this API design?" --mode review
Action: Codex evaluation -> Claude verification -> Output issues + recommendations

© sd0xdev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/codex-architect of sd0xdev/sd0x-harness.

• SKILL.md
• references/project-knowledge.md

Open the folder on GitHubat commit c9a2036