codex-advisor

codex-advisor is a skill for Claude Code, Codex from and3r817/dot-claude-plugins. It costs 85 tokens per session (2,838 once invoked), scanned A, original, MIT.

An advisory skill for getting engineering feedback from Codex, an AI coding assistant. It supports open-ended discussion and structured reviews of important technical choices, without changing code.

In plain words
What is it for?
Brainstorming solutions, reviewing code or architecture, comparing technologies, and evaluating high-stakes engineering decisions.
Why use it?
It provides a separate review of architecture, designs, code, technology choices, or plans before implementation. This helps surface trade-offs and risks before work begins.

Skill for Claude CodeCodex

Part of the codex-advisor plugin — 1 skill shipped together

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 skills/and3r817/dot-claude-plugins/codex-advisor
Any agent
npx skills add and3r817/dot-claude-plugins --skill codex-advisor
Clone the repo
git clone --depth 1 https://github.com/and3r817/dot-claude-plugins

Made for: Claude Code, Codex.

Or install codex-advisor, the plugin that ships this one along with the rest of its 1 skill.

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 codex-advisor

README.md
[![agentmods](https://agentmods.dev/badge/skills/and3r817/dot-claude-plugins/codex-advisor.svg)](https://agentmods.dev/skills/and3r817/dot-claude-plugins/codex-advisor)
Your own site
<a href="https://agentmods.dev/skills/and3r817/dot-claude-plugins/codex-advisor"><img src="https://agentmods.dev/badge/skills/and3r817/dot-claude-plugins/codex-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,838 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00085 $0.02838
Opus 5 $0.00043 $0.01419
Sonnet 5 $0.00017 $0.00568
Haiku 4.5 $0.00009 $0.00284

Measured 5d ago against content hash fbafe35f3e30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-advisor 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 5d 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.

codex-advisor/skills/codex-advisor/SKILL.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Advisor

Use this skill to consult Codex as a senior engineering advisor through two specialized collaboration modes: Chat for peer brainstorming and Consensus for structured evaluation. Invoke Codex strictly for advisory consultation—it provides analysis and recommendations while Claude handles all code implementation.

Collaboration Modes

Chat Mode — Peer brainstorming for exploring solutions, trade-offs, and validation. Use for iterative problem-solving and technical discussions. See references/chat-pattern.md for detailed guidance.

Consensus Mode — Structured evaluation for major decisions. Provides 7-dimension assessment with verdict and confidence scoring. Use for high-stakes architectural or technology decisions. See references/consensus-pattern.md for detailed guidance.

When to Use This Skill

Invoke Codex for advisory consultation on architecture, design decisions, code review, technology selection, and strategic planning. Codex provides analysis and recommendations only—all code implementation uses Claude's tools directly.

Do not use for: Simple questions, actual code writing, or file modifications.

Collaboration Workflow

Step 1: Load Project Context (Always Do This First)

Before consulting Codex, gather project-specific context to ensure recommendations align with established constraints:

Required:

  1. Read ~/.claude/CLAUDE.md for global project principles and constraints
  2. Extract key information:
    • Core principles (e.g., "INVESTIGATE BEFORE CHANGING", "MINIMAL SURGICAL CHANGES")
    • Forbidden patterns or practices
    • Architecture constraints
    • Code style requirements
    • Security/quality standards

Optional:

  • If project-specific ./AGENTS.md exists in current directory, read it for additional context

Usage:

  • Include extracted constraints in your prompt to Codex, OR
  • Add them as context in the developer-instructions parameter

Example context to include:

Project constraints from CLAUDE.md:
- INVESTIGATE BEFORE CHANGING: debug systematically first
- MINIMAL SURGICAL CHANGES: change only what's requested
- FOLLOW EXISTING PATTERNS: match codebase conventions
- No placeholders or fallback implementations

Read the full file on GitHub · 384 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 384 lines · 85 tokens per session scan A fbafe35f3e30

Subscribe to this mod's changes

codex-advisor is a skill published in the GitHub repository and3r817/dot-claude-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 85 tokens to every session and 2,838 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

orchestrator

FULLY AUTONOMOUS Flutter development pipeline orchestrator. Smart routing: PM analyzes -> creates targeted tasks -> Orchestrator executes only needed agents. Supports Asana task URLs. Includes QE verification via Maestro E2E tests. 7-phase flow: PM -> TodoWrite -> Execute -> Review -> Tests -> QE E2E -> Close.

aleksandr-chaika/flutter-clean-arch-skills · 72 tokens

flutter-guide

Flutter/BLoC Clean Architecture patterns, review checklists, and testing guides. Background knowledge for flutter-dev, flutter-reviewer, flutter-tester. Not user-invocable.

aleksandr-chaika/flutter-clean-arch-skills · 39 tokens

maestro-flutter

Maestro E2E testing knowledge for Flutter apps. YAML-based flows, TestKeys, visual regression, Maestro MCP integration. Background knowledge for QE E2E testing phase.

aleksandr-chaika/flutter-clean-arch-skills · 41 tokens

auditing-readme

Audit README.md files against best practices for repos, accounts, or orgs. Detects missing sections, stale links, inconsistent formatting, and convention violations. Use when reviewing README quality across one or many repos.

qte77/claude-code-plugins · 47 tokens

synthesizing-cc-bigpicture

Synthesizes a living big-picture meta-plan from Claude Code sessions, plans, tasks, and team communications. Use when orienting across projects, assessing reasoning modes, or creating a plan-to-plan overview.

qte77/claude-code-plugins · 0 tokens

enforcing-doc-hierarchy

Audit documentation against its declared hierarchy — broken links, duplicates, misplaced content, stale references, single-source-of-truth enforcement. Use for doc health reviews.

qte77/claude-code-plugins · 37 tokens