loop-forge

loop-forge is a command for coding agents from sangrokjung/claude-forge. It costs 21 tokens per session (460 once invoked), scanned A, original, MIT.

A command that turns a repetitive task described in one line into a reusable slash command. It asks for the needed details, classifies the task into one of five patterns, checks safety, and shows a preview before creating it.

In plain words
What is it for?
Use it to build reusable commands for batch work, step-by-step pipelines, refinement tasks, monitoring, or exploration.
Why use it?
It records the repeated task and its safeguards so the same work does not have to be designed manually each time.

Command

Part of the claude-forge plugin — 5 skills, 35 commands, 17 agents shipped together

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/sangrokjung/claude-forge/loop-forge
Clone the repo
git clone --depth 1 https://github.com/sangrokjung/claude-forge

Or install claude-forge, the plugin that ships this one along with the rest of its 5 skills, 35 commands, 17 agents.

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 loop-forge

README.md
[![agentmods](https://agentmods.dev/badge/commands/sangrokjung/claude-forge/loop-forge.svg)](https://agentmods.dev/commands/sangrokjung/claude-forge/loop-forge)
Your own site
<a href="https://agentmods.dev/commands/sangrokjung/claude-forge/loop-forge"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/loop-forge.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 460 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 $0.00021 $0.00460
Opus 5 $0.00010 $0.00230
Sonnet 5 $0.00004 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 3d ago against content hash 12b1ada51239, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-forge 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 3d 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.

commands/loop-forge.md · 34 lines

What it actually says

/loop-forge

Hand the one-line situation in $ARGUMENTS to the loop-forge skill and run its 6-stage flow exactly as written in skills/loop-forge/SKILL.md:

  1. Entry — read the situation from $ARGUMENTS. If empty, ask (in the user's language): "What task do you keep doing by hand? Describe it in one line."
  2. Diagnose — classify it into one of the 5 loop shapes (Batch / Pipeline / Refine / Watch / Explore). Never invent a sixth.
  3. Interview — ask the shape's slot questions in plain language; re-ask the output location, the hardstop inputs, and the eval criteria if left blank.
  4. Assemble + auto-inject safety + static check — substitute the slots, inject the verifier (maker ≠ checker), the hardstop, and (for outbound actions) the external-action gate, then run tools/check_safety.py. The gate is non-bypassable: exit 2 bounces back to the interview.
  5. Dry-run preview — show how it will run and get explicit approval. No approval, no stamping.
  6. Stamp — render the reusable /command (and, optionally, the Portable Prompt) and tell the user how to run it.

This command is a thin entry point. The authoritative procedure, the 5 archetype catalogs, the classifier, the interviewer, the assembler, the renderers, and the deterministic safety gate all live under skills/loop-forge/. Follow SKILL.md — do not re-implement the flow here.

Non-goals (preserved): loop-forge does not schedule unattended runs (launchd/cron) and never publishes externally on its own. It stamps the reusable command and stops there.

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. 3d ago First seen · 34 lines · 21 tokens per session scan A 12b1ada51239

Subscribe to this mod's changes

loop-forge is a command published in the GitHub repository sangrokjung/claude-forge (821 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 460 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 2026-08-30.