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 instructions/zts0hg/codexspec/claude-mdgit clone --depth 1 https://github.com/Zts0hg/codexspecWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/zts0hg/codexspec/claude-md)<a href="https://agentmods.dev/instructions/zts0hg/codexspec/claude-md"><img src="https://agentmods.dev/badge/instructions/zts0hg/codexspec/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.11507 | $0.11507 |
| Opus 5 | $0.05754 | $0.05754 |
| Sonnet 5 | $0.02301 | $0.02301 |
| Haiku 4.5 | $0.01151 | $0.01151 |
Grade A, and why
codexspec CLAUDE.md 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 today.
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 — 811 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@.codexspec/memory/constitution.md @docs/internal/repository-layout.md
CLAUDE.md - CodexSpec Development Guide
This document provides comprehensive context and guidelines for Claude Code when working on the CodexSpec project itself.
Project Overview
CodexSpec is a Requirements-First SDD toolkit for Claude Code. It is a Python CLI tool that can be installed via uv tool install and provides structured slash commands for AI-assisted software development.
Purpose
CodexSpec helps developers:
- Establish project principles through a constitution
- Create detailed specifications focused on "what" and "why"
- Generate technical implementation plans
- Break down plans into actionable tasks
- Execute implementations systematically
- Validate quality through checklists and analysis
Technology Stack
- Language: Python 3.11+
- CLI Framework: Typer (with Rich for formatting)
- Package Manager: uv
- Build System: Hatchling
- Testing: pytest
- Linting: ruff
Architecture
CLI Architecture
The CLI is built using Typer and follows a modular structure:
# Main entry point
app = typer.Typer(
name="codexspec",
help="CodexSpec - A Requirements-First SDD toolkit for Claude Code",
)
# Commands
@app.command()
def init(...): ...
@app.command()
def check(...): ...
@app.command()
def version(...): ...
@app.command()
def config(...): ... # NEW: Configuration management
Internationalization (i18n) Architecture
CodexSpec uses LLM-based dynamic translation for internationalization instead of maintaining multiple template translations.
Core Concept: Keep templates in English, let Claude translate at runtime based on user's language preference.
Implementation:
src/codexspec/i18n.py- Language utilities (normalization, validation).codexspec/config.yml- Per-project language configuration- Template
## Language Preferencesection - Instructs Claude to check config
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.
- today Changed · +32 lines · +1,465 tokens per session 4d399f3c1d42
- 4d ago First seen · 779 lines · 10,042 tokens per session scan A ce07d28ac8fe
codexspec CLAUDE.md is an instructions file published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 2d ago), licensed MIT. It adds 11,507 tokens to every session, about $0.0575 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 2026-08-31.
Other instructions, from other repositories
agentready AGENTS.md
AGENTS.md instructions for ambient-code/agentready, covering agentready, commands, core, development and data flow.
agentready CLAUDE.md
Claude Code instructions for ambient-code/agentready, a project described as: Repo Optimizer: Assess git repositories for AI-assisted development readiness. Submit your score!
apm python.instructions.md
Python development guidelines.
claude-code-templates CLAUDE.md
Claude Code instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.
ai-cli-utils GEMINI.md
Gemini CLI instructions for sergeiwallace/ai-cli-utils, covering ai-cli-utils — gemini context, tech stack, development conventions, public open-source package standards and ai sync scope boundary.