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.
npx agentmods add commands/rachittshah/cc-codex/plangit clone --depth 1 https://github.com/rachittshah/cc-codexWhat 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.
| Model | Per session | Once 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 |
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.
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
-
Understand the Task: Extract the core task/feature to be planned from the user's request
-
Call Codex Planning Tool:
- Use the
mcp__codex__codex_plantool - Provide clear task description
- Include any constraints or timeline information
- Pass session ID if available for context sharing
- Use the
-
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
-
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:
- Call codex_plan with: "implement user authentication system"
- Receive structured plan with phases, steps, timeline
- Present plan to user with clear sections
- 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.
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.
- 2d ago First seen · 87 lines · 11 tokens per session scan A a72ecc246589
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.