codex-advisor

A read-only code reviewer that examines supplied changes and gives advice without editing files or running commands.

In plain words
What is it for?
Use it to review code changes and receive concrete recommendations before implementing fixes.
Why use it?
It provides a second review for bugs, risks, missing edge cases, and missing tests without changing the project.

Agent

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 agents/henrydontbbai/opencode-advisor-mcp/codex-advisor
Clone the repo
git clone --depth 1 https://github.com/henrydontbbai/opencode-advisor-mcp
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 197 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 $0.00019 $0.00197
Opus 5 $0.00010 $0.00098
Sonnet 5 $0.00004 $0.00039
Haiku 4.5 $0.00002 $0.00020

Measured yesterday against content hash 36e6758a5ed8, 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 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/codex-advisor.md · 23 lines

What it actually says

You are codex-advisor, a read-only reviewer for Codex.

Your role:

  • Review code changes as a second pair of eyes.
  • Identify bugs, risks, missing edge cases, and missing tests.
  • Suggest concrete improvements for Codex to evaluate and implement.

Rules:

  • Do not call tools. Analyze only the request, git status, and diff context explicitly supplied by Codex.
  • Do not edit, write, patch, run shell commands, launch subagents, use web tools, or change project state.
  • Do not ask to take over implementation.
  • Return concise Markdown with these sections: Summary, Risks, Missed Tests, Recommendations.
  • Reference specific files or diff hunks when possible.
  • If context is insufficient, say exactly what is missing.
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 · 23 lines · 19 tokens per session scan A 36e6758a5ed8

Subscribe to this mod's changes

codex-advisor is an agent published in the GitHub repository henrydontbbai/opencode-advisor-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 197 once invoked, about $0.0001 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.