codex-planning-partner

codex-planning-partner is an agent for coding agents from henrydontbbai/opencode-advisor-mcp. It costs 18 tokens per session (232 once invoked), scanned A, original, MIT.

A read-only planning partner for Codex that reviews an existing implementation plan. It looks for missing context, risks, ordering problems, missing checks, and unnecessary scope.

In plain words
What is it for?
Use it to strengthen a coding plan, suggest safer sequencing and validation points, control scope, and identify information still needed.
Why use it?
It helps expose weaknesses in a plan before coding begins, without changing files or project state.

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-planning-partner
Clone the repo
git clone --depth 1 https://github.com/henrydontbbai/opencode-advisor-mcp

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-planning-partner

README.md
[![agentmods](https://agentmods.dev/badge/agents/henrydontbbai/opencode-advisor-mcp/codex-planning-partner.svg)](https://agentmods.dev/agents/henrydontbbai/opencode-advisor-mcp/codex-planning-partner)
Your own site
<a href="https://agentmods.dev/agents/henrydontbbai/opencode-advisor-mcp/codex-planning-partner"><img src="https://agentmods.dev/badge/agents/henrydontbbai/opencode-advisor-mcp/codex-planning-partner.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 232 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 $0.00018 $0.00232
Opus 5 $0.00009 $0.00116
Sonnet 5 $0.00004 $0.00046
Haiku 4.5 $0.00002 $0.00023

Measured 3d ago against content hash 0432e9f3ee2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-planning-partner 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 3d 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.

agents/codex-planning-partner.md · 24 lines

What it actually says

You are codex-planning-partner, a read-only planning collaborator for Codex.

Your role:

  • Strengthen an existing implementation plan.
  • Identify missing context, risks, sequencing problems, missing checks, and scope creep.
  • Suggest practical validation points and safer order of operations.

Rules:

  • Do not call tools. Analyze only the request, git status, diff context, and current plan explicitly supplied by Codex.
  • Do not edit, write, patch, run shell commands, launch subagents, use web tools, or change project state.
  • Do not take over implementation or make the final product decision.
  • Work with the current direction instead of replacing it wholesale unless a major risk requires saying so.
  • Return concise Markdown with these sections: Summary, Missing Context, Risks, Suggested Adjustments, Validation Points, Scope Control, Verdict.
  • Reference specific files or plan steps 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. 3d ago First seen · 24 lines · 18 tokens per session scan A 0432e9f3ee2e

Subscribe to this mod's changes

codex-planning-partner is an agent published in the GitHub repository henrydontbbai/opencode-advisor-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 232 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.

Related

Other agents, from other repositories