plan

A command that creates a detailed implementation plan for a requested coding task using Codex's reasoning model.

In plain words
What is it for?
Use it to turn a feature request into a structured plan and decide whether to proceed with implementation.
Why use it?
It breaks a broad request into phases, dependencies, risks, and next steps before implementation begins.

Command

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 commands/rachittshah/cc-codex/plan
Clone the repo
git clone --depth 1 https://github.com/rachittshah/cc-codex
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 495 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 $0.00011 $0.00495
Opus 5 $0.00005 $0.00247
Sonnet 5 $0.00002 $0.00099
Haiku 4.5 $0.00001 $0.00049

Measured 2d ago against content hash a72ecc246589, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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 2d 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.

commands/plan.md · 87 lines

What it actually says

Generate Implementation Plan

Your task

You are receiving a request to create a detailed implementation plan using Codex's deep reasoning capabilities.

Steps

  1. Understand the Task: Extract the core task/feature to be planned from the user's request

  2. Call Codex Planning Tool:

    • Use the mcp__codex__codex_plan tool
    • Provide clear task description
    • Include any constraints or timeline information
    • Pass session ID if available for context sharing
  3. Process the Plan:

    • Parse the structured plan output from Codex
    • Present it in a clear, readable format
    • Highlight key phases and next steps
    • Note any risks or dependencies
  4. Ask for Feedback:

    • Ask if the user wants to proceed with implementation
    • Offer to refine the plan if needed
    • Suggest starting with the first phase/step

Example Usage

User: "/plan implement user authentication system"

Expected flow:

  1. Call codex_plan with: "implement user authentication system"
  2. Receive structured plan with phases, steps, timeline
  3. Present plan to user with clear sections
  4. Ask: "Would you like me to start implementing Phase 1?"

Notes

  • This delegates planning to Codex (gpt-5 with high reasoning)
  • Claude Code (you) will handle the actual implementation
  • The plan becomes a shared artifact in the session context
  • Use the plan to guide step-by-step implementation

Output Format

Present the plan like this:

# Implementation Plan: [Task Name]

## Overview
[High-level summary]

## Phase 1: [Name]
**Steps**:
1. [Step description] (est: [duration])
   - Dependencies: [if any]
   - Risks: [if any]

[... more steps ...]

## Technologies Required
- [Tech 1]
- [Tech 2]

## Timeline
[Overall estimate]

## Risks
- [Risk 1]
- [Risk 2]

## Next Steps
1. [Immediate action 1]
2. [Immediate action 2]

---

Ready to proceed with Phase 1? I can start implementing now.
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. 2d ago First seen · 87 lines · 11 tokens per session scan A a72ecc246589

Subscribe to this mod's changes

plan is a command published in the GitHub repository rachittshah/cc-codex (11 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 495 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 2026-08-30.