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.
curl -O https://raw.githubusercontent.com/TheAstrelo/Claude-Pipeline/main/.claude/commands/arm.mdgit clone --depth 1 https://github.com/TheAstrelo/Claude-PipelineWrote 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/commands/theastrelo/claude-pipeline/arm)<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>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 5.1 | $0.00000 | $0.00395 |
| Opus 5 | $0.00000 | $0.00198 |
| Sonnet 5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00040 |
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.
What it actually says
Crystallize requirements for the following task:
$ARGUMENTS
Session Management
First, create a new session directory for this task:
- Generate a timestamp and task slug:
{YYYYMMDD-HHMMSS}-{task-slug} - Create directory:
.claude/artifacts/{timestamp}-{task-slug}/ - Update
.claude/artifacts/current.txtwith the path to the new session directory
Use Bash to create the directory:
# Create session directory with timestamp
SESSION_DIR=".claude/artifacts/$(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:
- Parse the task description above for ambiguities
- Explore the codebase to understand relevant existing code
- 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)
- Ask the user these questions
- Iterate until requirements are clear (max 3 rounds)
- Output
brief.mdto 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.
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.
- 8d ago First seen · 69 lines · 0 tokens per session scan A 1f0a65f50230
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.
Other commands, from other repositories
status
Summarise what Fabrik is doing right now — board state, in-flight workers, worktrees with uncommitted changes.
setup-forge
First-run onboarding — asks name/goal/project-type/language, then beginner-safe API-key setup, then scaffolds the per-project Forge system. User-invoked only. Run once per project. Subcommands: doctor · keys · reset.
spreadsheet-audit
Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.
custom-brief
Deep-research a specific topic and produce a comprehensive news-focused briefing with optional Notion/Obsidian/Teams/Slack publishing.
diagnose-roast-curve
Diagnose a logged roast curve for the classic defects — crash, flick, stall/bake, tipping, scorching — and assess RoR smoothness and development-time ratio.
gsd:resume-work
Resume work from previous session with full context restoration.