codex

A command for sending a request to a specialised Codex task, such as reasoning, planning, specification writing, analysis, or comparison.

In plain words
What is it for?
Use it for trade-off decisions, project plans, technical specifications, code or architecture reviews, and comparisons of options.
Why use it?
It helps route different kinds of work to the matching task instead of treating every request the same way.

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/codex
Clone the repo
git clone --depth 1 https://github.com/rachittshah/cc-codex
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 745 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 $0.00016 $0.00745
Opus 5 $0.00008 $0.00373
Sonnet 5 $0.00003 $0.00149
Haiku 4.5 $0.00002 $0.00075

Measured 2d ago against content hash c58c41487a52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex 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/codex.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute Custom Codex Task

Your task

You are receiving a request to execute a custom Codex task. Determine which Codex tool is most appropriate and execute it.

Available Codex Tools

  1. codex_reason: Deep reasoning, trade-off analysis, decision-making
  2. codex_plan: Implementation planning, project roadmaps
  3. codex_spec: Technical specifications, documentation
  4. codex_analyze: Code/architecture analysis, security/performance review
  5. codex_compare: Compare multiple options/technologies

Steps

  1. Analyze Request: Determine which Codex tool matches the request

    • Keywords like "plan" → codex_plan
    • Keywords like "should we" → codex_reason
    • Keywords like "specification" → codex_spec
    • Keywords like "analyze" → codex_analyze
    • Keywords like "compare" → codex_compare
  2. Execute Codex Tool: Call the appropriate tool with proper parameters

  3. Present Results: Format and present the Codex output clearly

  4. Follow Up: Suggest next steps based on the output

Example Usage

User: "/codex compare Redis vs Memcached for our caching layer"

Expected flow:

  1. Detect: This is a comparison task
  2. Call codex_compare with options ["Redis", "Memcached"]
  3. Receive structured comparison
  4. Present formatted comparison
  5. Ask: "Based on this comparison, shall we proceed with [recommendation]?"

Task Type Detection

"plan" | "roadmap" | "timeline" | "phases"
  → codex_plan

"should we" | "which is better" | "decide" | "reason"
  → codex_reason

"spec" | "specification" | "document" | "requirements"
  → codex_spec

"analyze" | "review" | "audit" | "examine"
  → codex_analyze

"compare" | "versus" | "vs" | "which one"
  → codex_compare

Notes

  • This is a meta-command that routes to specific Codex tools
  • All Codex tools use gpt-5 with high reasoning effort
  • Results are stored in shared session context
  • Can chain multiple Codex calls if needed

Example Scenarios

Scenario 1: Architecture Decision

User: /codex should we use microservices or monolith?
→ Use codex_reason

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 16 tokens per session scan A c58c41487a52

Subscribe to this mod's changes

codex is a command published in the GitHub repository rachittshah/cc-codex (11 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 745 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.