codex-plan

A command that creates a detailed software implementation plan with help from a Codex coding model. It first examines the request and asks questions about unclear requirements.

In plain words
What is it for?
Use it before coding features, migrations, integrations, or other projects where decisions and requirements need to be clarified and documented.
Why use it?
It helps turn a broad or incomplete development request into a plan that reflects the needed scope, technology, constraints, and security concerns.

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/softaworks/agent-toolkit/codex-plan
Clone the repo
git clone --depth 1 https://github.com/softaworks/agent-toolkit
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,668 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00015 $0.02668
Opus 5 $0.00008 $0.01334
Sonnet 5 $0.00003 $0.00534
Haiku 4.5 $0.00002 $0.00267

Measured yesterday against content hash 0b3c3fc563cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-plan scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

7. **Output instructions** - Write to `codex-plan.md` in current directory
commands/codex-plan.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Plan Command

You are being asked to create a detailed implementation plan using a Codex subagent. Your job is to:

  1. Understand the user's planning request
  2. Ask clarifying questions using AskUser to improve plan quality
  3. Craft an excellent, detailed prompt for Codex
  4. Execute Codex to generate and save the plan

Always uses: gpt-5.2-codex with high reasoning

User Request

$ARGUMENTS

Step 1: Analyze the Request

Look at what the user wants to plan. Identify:

  • What is the core goal?
  • What technology/domain is involved?
  • What aspects are ambiguous or underspecified?
  • What decisions would significantly impact the plan?

Step 2: Ask Clarifying Questions

Use AskUser to ask 3-6 targeted clarifying questions before generating the plan.

Good clarifying questions:

  • Narrow down scope and requirements
  • Clarify technology choices
  • Understand constraints (time, budget, team size)
  • Identify must-haves vs nice-to-haves
  • Uncover integration requirements
  • Determine security/compliance needs

Example Question Patterns

For "implement auth":

  • What authentication methods do you need? (email/password, OAuth providers like Google/GitHub, SSO, magic links)
  • Do you need role-based access control (RBAC) or just authenticated/unauthenticated?
  • What's your backend stack? (Node/Express, Python/Django, etc.)
  • Where will you store user credentials/sessions? (Database, Redis, JWT stateless)
  • Do you need features like: password reset, email verification, 2FA?
  • Any compliance requirements? (SOC2, GDPR, HIPAA)

For "build an API":

  • What resources/entities does this API need to manage?
  • REST or GraphQL?
  • What authentication will the API use?
  • Expected scale/traffic?
  • Do you need rate limiting, caching, versioning?

For "migrate to microservices":

  • Which parts of the monolith are you migrating first?
  • What's your deployment target? (K8s, ECS, etc.)
  • How will services communicate? (REST, gRPC, message queues)
  • What's your timeline and team capacity?

Read the full file on GitHub · 320 lines

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 · 320 lines · 15 tokens per session scan B 0b3c3fc563cb

Subscribe to this mod's changes

codex-plan is a command published in the GitHub repository softaworks/agent-toolkit (2,401 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 2,668 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.