execute-loop

An execution command that runs the current l00prite project plan through repeated development iterations after a required human confirmation.

In plain words
What is it for?
Use it to continue a scaffolded project's implementation, review its pre-flight summary, and run the defined build, test, and progress loop after confirming.
Why use it?
It prevents autonomous changes from starting accidentally and keeps execution tied to the project's stored instructions and progress records.

Command for Claude Code

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/jackofall1232/l00prite/execute-loop
Clone the repo
git clone --depth 1 https://github.com/jackofall1232/l00prite

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 385 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 $0.00030 $0.00385
Opus 5 $0.00015 $0.00192
Sonnet 5 $0.00006 $0.00077
Haiku 4.5 $0.00003 $0.00038

Measured yesterday against content hash 9a555bcc7b2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute-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 yesterday.

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/execute-loop.md · 32 lines

What it actually says

You are running the /execute-loop command from the l00prite project. This command enters Execution Mode for the l00prite-managed project in the current working directory.

Read the current repo's canonical execute-loop prompt and follow it exactly — the pre-flight gate, the iteration protocol, the nine run boundaries, and the hard rules are all defined there. In a scaffolded project it lives at l00prite/.l00prite/prompts/execute-loop.md; in a repo whose memory sits at the root (like the l00prite source repo itself) it is .l00prite/prompts/execute-loop.md. If the current repo has neither, follow .claude/prompts/execute-loop.md from this repo instead (they are byte-identical mirrors).

Optional context from the user for this run (goal, scope limits, or constraints to include in the pre-flight display):

$ARGUMENTS

Non-negotiable, regardless of arguments:

  • Do not begin any iteration before the pre-flight summary has been displayed and the human has explicitly confirmed in this session. A preflight_confirmed: true or execution.enabled: true already sitting in heartbeat.json does not satisfy the gate — re-confirm every run.
  • If neither l00prite/.l00prite/ nor .l00prite/ exists here, this project isn't l00prite-managed yet: stop and point the user at /build-loop (Planning Mode) instead of improvising memory files.
  • Respect every run boundary in the prompt, including the special no-write rule for lock_lease_conflict.
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. yesterday First seen · 32 lines · 30 tokens per session scan A 9a555bcc7b2e

Subscribe to this mod's changes

execute-loop is a command published in the GitHub repository jackofall1232/l00prite (9 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 385 once invoked, about $0.0002 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.