Claude-Pipeline: Command for Claude Code

.claude/commands/arm.md

arm is a command for Claude Code from TheAstrelo/Claude-Pipeline. It costs 0 tokens per session (395 once invoked), scanned A, original, MIT.

A command that turns a task description into a clearer set of requirements by examining the codebase and asking grouped follow-up questions.

In plain words
What is it for?
Use it at the start of a coding task to create a requirements brief and record the discussion in a task-specific session folder.
Why use it?
It exposes unclear scope, edge cases, constraints, and dependencies before implementation begins.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is TheAstrelo/Claude-Pipeline's own configuration. It tells Claude Code how to work on Claude-Pipeline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Pipeline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TheAstrelo/Claude-Pipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TheAstrelo/Claude-Pipeline/main/.claude/commands/arm.md
Clone the repo
git clone --depth 1 https://github.com/TheAstrelo/Claude-Pipeline

Made for: Claude Code.

Wrote 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.

agentmods badge for arm

README.md
[![agentmods](https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/arm.svg)](https://agentmods.dev/commands/theastrelo/claude-pipeline/arm)
Your own site
<a href="https://agentmods.dev/commands/theastrelo/claude-pipeline/arm"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/arm.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00395
Opus 5 $0.00000 $0.00198
Sonnet 5 $0.00000 $0.00079
Haiku 4.5 $0.00000 $0.00040

Measured 8d ago against content hash 1f0a65f50230, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

arm 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 8d 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/arm.md · 69 lines

What it actually says

Crystallize requirements for the following task:

$ARGUMENTS


Session Management

First, create a new session directory for this task:

  1. Generate a timestamp and task slug: {YYYYMMDD-HHMMSS}-{task-slug}
  2. Create directory: .claude/artifacts/{timestamp}-{task-slug}/
  3. Update .claude/artifacts/current.txt with the path to the new session directory

Use Bash to create the directory:

# Create session directory with timestamp
SESSION_DIR=".claude/artifacts/$(date +%Y%m%d-%H%M%S)-{task-slug}"
mkdir -p "$SESSION_DIR"
echo "$SESSION_DIR" > .claude/artifacts/current.txt

Requirements Crystallization

Use the requirements-crystallizer agent.

Process:

  1. Parse the task description above for ambiguities
  2. Explore the codebase to understand relevant existing code
  3. Generate 5-10 clarifying questions grouped by theme:
    • Scope (what's in/out)
    • Behavior (edge cases, feedback, inputs/outputs)
    • Constraints (performance, security, compatibility)
    • Dependencies (APIs, database, other features)
  4. Ask the user these questions
  5. Iterate until requirements are clear (max 3 rounds)
  6. Output brief.md to the session directory

Output

After crystallization, report:

## Requirements Crystallization Complete

**Session:** {session-directory}
**Verdict:** [CRYSTALLIZED | NEEDS_CLARIFICATION]

### Problem Statement
[Summary from brief.md]

### Success Criteria
[Key criteria from brief.md]

### Next Step
Run `/design` to create the technical design.

Gate

This command creates the session and brief.md. The /design command requires this to exist.

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. 8d ago First seen · 69 lines · 0 tokens per session scan A 1f0a65f50230

Subscribe to this mod's changes

arm is a command published in the GitHub repository TheAstrelo/Claude-Pipeline (44 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 395 tokens. 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.