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/specgit 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 | $0.00010 | $0.00596 |
| Opus 5 | $0.00005 | $0.00298 |
| Sonnet 5 | $0.00002 | $0.00119 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
spec 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Technical Specification
Your task
You are receiving a request to create a comprehensive technical specification using Codex.
Steps
-
Gather Requirements: Extract the feature/system to specify and any requirements
-
Call Codex Specification Tool:
- Use the
mcp__codex__codex_spectool - Provide title and description
- Include requirements list if available
- Pass session ID for context
- Use the
-
Process the Spec:
- Parse the structured specification
- Present in a clear, professional format
- Include all sections: requirements, architecture, API, implementation
- Make it implementation-ready
-
Validate with User:
- Ask if the spec is complete
- Offer to refine specific sections
- Suggest saving as documentation
- Propose starting implementation
Example Usage
User: "/spec create a specification for rate limiting middleware"
Expected flow:
- Call codex_spec with title and description
- Receive comprehensive spec with architecture, API, implementation plan
- Present formatted specification
- Ask: "Spec complete. Shall I implement this now?"
Notes
- Use for documenting new features/systems
- Spec becomes the source of truth
- Can be saved as .md file in docs/
- Reference during implementation
Output Format
Present the specification like this:
# Technical Specification: [Title]
## Overview
[High-level description]
## Requirements
### Functional Requirements
1. [Requirement 1]
2. [Requirement 2]
### Non-Functional Requirements
1. [Performance requirement]
2. [Security requirement]
3. [Scalability requirement]
## Architecture
### Components
#### [Component 1]
**Responsibilities**:
- [Responsibility 1]
- [Responsibility 2]
#### [Component 2]
[... same structure ...]
### Data Flow
[Description of how data flows through the system]
### External Integrations
- [Integration 1]
- [Integration 2]
## API Design
### Endpoint: [METHOD] /path
**Description**: [What it does]
**Request**:
```json
{
"field": "type"
}
Response:
{
"result": "data"
}
Implementation
Phases
- [Phase 1 description]
- [Phase 2 description]
Technologies
- [Technology 1]
- [Technology 2]
Estimated Effort
[Time estimate]
Specification complete. Would you like me to:
- Save this as docs/[filename].md
- Start implementing Phase 1
- Refine any section
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 · 130 lines · 10 tokens per session scan A 1b759aacc5fc
spec is a command published in the GitHub repository rachittshah/cc-codex (11 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 596 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
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.