agentleFS
Sign inStart free
sd0xdevsd0xdev/sd0x-dev-flow/skills/codex-architect/SKILL.md

codex-architect

Skill192 starsChanged 36 days agoMITView on GitHub

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.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When dispatching per @skills/codex-code-review/references/codex-transport.md § Start, the prompt must include the following:

    line 45
  2. Distinctive:

    Before providing architecture advice, you must perform the following research:

    line 59
  3. Very specific:

    Search related modules: grep -rn "keyword" .

    line 64
  4. Very specific:

    Read existing implementations: cat <relevant files> | head -150

    line 65
  5. Distinctive:

    Consider consistency with existing architecture

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Codex Architect Skill (Third Brain)

Trigger

  • Keywords: architecture design, solution evaluation, tech selection, third brain, Codex advice, design consulting, ask Codex, second opinion

When NOT to Use

  • Code implementation (use /codex-implement)
  • Code review (use /codex-review)
  • Deep discussion/exhaustive exploration (use /codex-brainstorm)

Usage

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

Modes

ModePurposeWhen
designProvide design adviceStarting from scratch (default)
reviewEvaluate existing designValidate solution, find issues
compareCompare multiple optionsTech selection

Core Principle

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

Codex Prompt Template

When dispatching per @skills/codex-code-review/references/codex-transport.md § Start, the prompt must include the following:

You are a senior architect. Please provide architecture advice for the following question.

Question

${QUESTION}

Mode

${MODE} (design/review/compare)

IMPORTANT: You must independently research the project

Before providing architecture advice, you must perform the following research:

Research Steps

  1. Understand the project structure by discovering it: ls at the repository root, then list the directories it actually shows — do not assume a src/ or test/unit/ layout; many repositories, this one included, have neither
  2. Search related modules: grep -rn "keyword" . -l | head -10 — rooted at the repository, or at a directory the discovery step above actually surfaced; never at an assumed src/
  3. Read existing implementations: cat <relevant files> | head -150
  4. Understand existing architecture patterns and conventions

Verification Focus

  • What does the existing architecture look like?
  • What are the existing code style and patterns?
  • What similar features can be referenced?

Output Requirements

  1. First describe which files you researched
  2. Provide advice based on current project state
  3. Consider consistency with existing architecture

...(other review dimensions)

Workflow Integration

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

Verification

  • Report includes Codex advice + Claude perspective
  • Consensus and divergence points clearly marked
  • Final recommendation integrates both perspectives

References

  • references/project-knowledge.md - Project architecture knowledge + report template

Examples

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free