commit-staged

A command that turns confirmed requirements into a technical specification document without changing the intended product behavior. It also follows project rules and records assumptions separately from confirmed decisions.

In plain words
What is it for?
Use it to generate or update spec.md from requirements.md and verified project information.
Why use it?
It gives developers a clearer implementation description while preserving the decisions that were actually agreed on.

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

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,699 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 $0.00018 $0.01699
Opus 5 $0.00009 $0.00849
Sonnet 5 $0.00004 $0.00340
Haiku 4.5 $0.00002 $0.00170

Measured 2d ago against content hash 5627d0099647, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-staged 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/commit-staged.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Constitution Compliance (MANDATORY)

Before generating commit messages:

  1. Check for Constitution File: Look for .codexspec/memory/constitution.md
  2. If Constitution Exists:
    • Load and read relevant principles (especially coding standards, commit conventions)
    • Ensure commit message style aligns with constitutional guidelines
    • Verify that the changes being committed don't violate any principles
  3. If No Constitution Exists: Proceed with default Conventional Commits format

Configuration Check

IMPORTANT: Before proceeding, check if the project configuration exists.

Execution Steps

  1. Check Configuration File

    • Check if .codexspec/config.yml exists
    • This is a simple file existence check, no parsing needed at this stage
  2. If Configuration Does NOT Exist

    • Display a one-time prompt:

      💡 Project language is not configured. Run `/codexspec:config` to create a configuration file.
      
    • Use default values for current session:

      • language.output: "en"
      • language.commit: "en"
      • language.templates: "en"
    • Continue with command execution normally

  3. If Configuration Exists

    • Proceed to ## Language Preference section
    • Read configuration and apply language settings as before
  4. Session State (Implicit)

    • The prompt is shown only once per conversation session
    • Claude's conversation context naturally maintains this state
    • No additional mechanism needed

Language Preference

IMPORTANT: Before generating commit messages, read the project's language configuration from .codexspec/config.yml.

Commit message language priority:

  1. If language.commit is set, use that language for the commit message description
  2. Otherwise, use language.output as fallback
  3. If neither is configured, default to English

Note:

  • The commit type (feat, fix, docs, etc.) and scope should always remain in English
  • Only the description part should use the configured language
  • Technical terms (e.g., API, JWT, OAuth) may remain in English when appropriate

Read the full file on GitHub · 170 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 · 170 lines · 18 tokens per session scan A 5627d0099647

Subscribe to this mod's changes

commit-staged is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 1,699 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.