new-module

A command that creates the starting files for a new module that connects to an application's core. A module is a self-contained part of a larger application.

In plain words
What is it for?
Use it to add a module with its source entry point, routes, scheduled jobs, registration test and codebase documentation.
Why use it?
It standardises the initial structure and checks the project's registration rules before files are created. This keeps setup separate from production logic.

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/nkhdiscovery/headless-agentic-codebase/new-module
Clone the repo
git clone --depth 1 https://github.com/nkhdiscovery/headless-agentic-codebase

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 247 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 $0.00009 $0.00247
Opus 5 $0.00005 $0.00123
Sonnet 5 $0.00002 $0.00049
Haiku 4.5 $0.00001 $0.00025

Measured yesterday against content hash 533d28cdcc20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-module 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 yesterday.

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/new-module.md · 27 lines

What it actually says

Scaffold a new module named: $ARGUMENTS

Before writing code:

  1. Read the relevant ADR for module registration (typically ADR 0003 or similar).
  2. Read docs/architecture.md to see where this module fits.
  3. Check the project manifest (pyproject.toml, package.json, etc.) for the module entry-point group.

Then create, in this order:

  1. <source_root>/$ARGUMENTS/__init__.py (or equivalent) — exports the Module class.
  2. <source_root>/$ARGUMENTS/routes.py — HTTP routes (empty if none).
  3. <source_root>/$ARGUMENTS/jobs.py — scheduled jobs (empty if none).
  4. tests/$ARGUMENTS/test_registration.py — module loads and registers correctly.
  5. docs/codebase/$ARGUMENTS.md — populate the seven-section template.
  6. Update the project manifest to declare the entry point.

Do NOT:

  • Reach into core internals beyond the registration API.
  • Write production logic in this scaffolding pass.

When done, run make test and report.

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. yesterday First seen · 27 lines · 9 tokens per session scan A 533d28cdcc20

Subscribe to this mod's changes

new-module is a command published in the GitHub repository nkhdiscovery/headless-agentic-codebase (10 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 247 once invoked, about $0.0000 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.