constitution

A command for creating or updating a project's constitution: a written set of principles that guides project work. It can take principles directly or explore them interactively.

In plain words
What is it for?
Use it to define or revise the rules that should guide requirements, specifications, plans, and other project documents.
Why use it?
It keeps project principles recorded and keeps documents based on shared templates aligned with them.

Command for Claude Code

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/zts0hg/codexspec/constitution
Clone the repo
git clone --depth 1 https://github.com/Zts0hg/codexspec

Made for: Claude Code.

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,633 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 $0.00025 $0.03633
Opus 5 $0.00013 $0.01817
Sonnet 5 $0.00005 $0.00727
Haiku 4.5 $0.00003 $0.00363

Measured 2d ago against content hash b56a8830d8b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

constitution 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.

.claude/commands/codexspec/constitution.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Language Preference

Read .codexspec/config.yml. Two independent language controls apply (each falls back to language.output, then English):

  • Interaction language (language.interaction): language for all conversation with the user — questions, explanations, status messages, and codexspec CLI terminal output.
  • Document language (language.document): language for generated artifact files (requirements/spec/plan/tasks).

Converse in the interaction language and author artifacts in the document language. Apply the project's translation standard to both: translate by meaning (not word-for-word), keep English for terms with no good native equivalent, and write as if originally in that language.

User Input

$ARGUMENTS

Input Mode Detection

Parse $ARGUMENTS to determine execution mode:

Mode A: No Arguments → Present exploration options and let user choose

Mode B: Exploration Keyword (quick or deep) → Execute the corresponding exploration mode

Mode C: Project Principles Description → Use provided principles directly, skip exploration


Mode A: No Arguments - Present Options

IMPORTANT: Use the host agent's structured-question tool (e.g., AskUserQuestion or request_user_input) to present structured choices.

{
  "questions": [{
    "question": "I will explore the project to generate the constitution. Please select exploration depth:",
    "header": "Exploration",
    "options": [
      {
        "label": "quick",
        "description": "Config files + README + core entry points (~5-10 files), best for newly initialized projects"
      },
      {
        "label": "deep",
        "description": "Above + full source code analysis + architecture patterns, best for mature projects"
      },
      {
        "label": "Describe principles",
        "description": "Skip exploration, I will tell you the project principles directly"
      }
    ]
  }]
}

Note: The field schema above follows the AskUserQuestion convention. Under request_user_input, each question additionally requires an id (snake_case) and accepts 2–3 options — follow the host tool's actual schema rather than copying this example verbatim.

Read the full file on GitHub · 408 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 · 408 lines · 25 tokens per session scan A b56a8830d8b2

Subscribe to this mod's changes

constitution is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 3,633 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 2026-08-31.