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.
npx agentmods add commands/sangrokjung/claude-forge/loop-forgegit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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/sangrokjung/claude-forge/loop-forge)<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>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 | $0.00021 | $0.00460 |
| Opus 5 | $0.00010 | $0.00230 |
| Sonnet 5 | $0.00004 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
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.
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:
- 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." - Diagnose — classify it into one of the 5 loop shapes (Batch / Pipeline / Refine / Watch / Explore). Never invent a sixth.
- 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.
- 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. - Dry-run preview — show how it will run and get explicit approval. No approval, no stamping.
- 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.
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.
- 3d ago First seen · 34 lines · 21 tokens per session scan A 12b1ada51239
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.
Other commands, from other repositories
build-agent
Scaffold a new AI DevOps agent — service, tool, or workflow subagent with YAML frontmatter, placement decision, and cross-reference discovery.
email-campaign
../../services/email/email-campaign.md.
email-delivery-test
../../services/email/email-delivery-test.md.
email-design-test
../../services/email/email-design-test.md.
email-health-check
../../services/email/email-health-check.md.
email-outreach
../../services/email/email-outreach.md.