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/jackofall1232/l00prite/build-loopgit clone --depth 1 https://github.com/jackofall1232/l00priteWhat 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 | $0.00070 | $0.04745 |
| Opus 5 | $0.00035 | $0.02372 |
| Sonnet 5 | $0.00014 | $0.00949 |
| Haiku 4.5 | $0.00007 | $0.00475 |
Grade A, and why
build-loop 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.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the /build-loop command from the l00prite project. This command is
Planning Mode: your job in this invocation is to scaffold a blueprint and persistent
loop memory, not to build anything. Planning Mode does not execute the project it
scaffolds. Follow the steps below in order. Do not skip ahead, do
not combine steps, and do not execute any part of the blueprint you produce — Execution
Mode is a separate, explicitly-confirmed handoff described in Step 8.
The user's project idea (if provided as an argument to this command) is:
$ARGUMENTS
If no idea was provided as an argument, ask the user to describe the project they want to
build before continuing to Step 1. If the arguments include the flag --execute, note it
now and apply Step 8 after the scaffold is complete; the flag changes nothing about Steps
1–7.
Step 1 — Ask clarifying questions (REQUIRED, do this first)
Before generating anything, ask the user for the following. Ask all of them together in one message, not one at a time:
- Project type — what kind of thing is this (CLI tool, web app, API/service, library, browser extension, WordPress/CMS plugin, data pipeline, mobile app, game, etc.)?
- Scope — what's the minimum viable version? What is explicitly out of scope for v1?
- Target languages/stack — programming language(s), frameworks, runtimes, package managers.
- Target repo — an existing local path/repo to scaffold into, or "new repo" (and if new, where should it live)?
- Hard constraints — deadlines, must-use libraries or APIs, deployment target, licensing requirements, anything else non-negotiable.
Do not proceed to Step 2 until the user has answered all five. The only exception: if the user explicitly says something like "use your judgment" for a given item, you may fill that one item in with a reasonable, clearly-labeled default — state the default you chose out loud. Do not silently assume defaults for items the user hasn't addressed at all.
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 · 295 lines · 70 tokens per session scan A 19051233715b
build-loop is a command published in the GitHub repository jackofall1232/l00prite (9 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 4,745 once invoked, about $0.0003 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.
Other commands, from other repositories
annotate-plan
Draft a plan and open it in the annotator UI for user review.
docs
Command "docs" from tilework-tech/nori-skillsets, covering noridoc: commands, how it fits into the larger codebase, core implementation and things to know.
add
Register a plugin in the catalog — reference a remote repo or scaffold a template.
init
Scaffold a new plugin marketplace, or a standalone plugin.
build
Generate the Codex and Cursor registries from the catalog.
bump
Version a local plugin from its commits and sync everything downstream.