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/reasongit 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 | $0.00502 |
| Opus 5 | $0.00005 | $0.00251 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
reason 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Reasoning Analysis
Your task
You are receiving a request for deep reasoning and analysis using Codex's advanced reasoning capabilities.
Steps
-
Understand the Question: Extract the core question or problem from the user's request
-
Call Codex Reasoning Tool:
- Use the
mcp__codex__codex_reasontool - Provide the question clearly
- Include any relevant context
- Pass session ID for context sharing
- Use the
-
Process the Analysis:
- Parse the structured reasoning output
- Present analysis, considerations, and approaches clearly
- Highlight the recommendation and rationale
- Show trade-offs transparently
-
Facilitate Decision:
- Ask if the user agrees with the recommendation
- Offer to explore alternative approaches
- Suggest concrete next steps
Example Usage
User: "/reason should we use REST or GraphQL for our API?"
Expected flow:
- Call codex_reason with the architectural question
- Receive analysis with multiple approaches evaluated
- Present structured comparison
- Ask: "Based on this analysis, shall we proceed with [recommendation]?"
Notes
- Use for architectural decisions, trade-off analysis, complex problems
- Codex provides multi-perspective analysis
- Present all options fairly, even if one is recommended
- Store reasoning as session artifact for future reference
Output Format
Present the reasoning like this:
# Reasoning: [Question]
## Analysis
[Detailed examination of the problem]
## Key Considerations
### [Factor 1] (Impact: High/Medium/Low)
[Description]
### [Factor 2] (Impact: High/Medium/Low)
[Description]
## Approaches Evaluated
### Approach 1: [Name]
**Complexity**: Low/Medium/High
**Pros**:
- [Pro 1]
- [Pro 2]
**Cons**:
- [Con 1]
- [Con 2]
### Approach 2: [Name]
[... same structure ...]
## Recommendation
[Recommended approach]
## Rationale
[Detailed reasoning for the recommendation]
---
Does this analysis align with your thinking? Ready to move forward with [recommendation]?
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 · 94 lines · 11 tokens per session scan A a4452dbc64f6
reason 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 502 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.