nauro-loop

nauro-loop is a cursor rule for Cursor from Nauro-AI/nauro. It costs 180 tokens per session (4,779 once invoked), scanned A, original, Apache-2.0.

A set of rules for managing work through defined stages: frame, choose, start, advise, verify, and advance. It requires human selection for work proposed by the agent and limits what the coordinator is allowed to change.

In plain words
What is it for?
Use it to coordinate delivery and interview work, review handoffs, verify completed steps, and recommend what happens next. User-named work follows a different entry path from work proposed by the agent.
Why use it?
It prevents the coordinator from automatically approving work, changing project records, or moving to the next task without the required review and selection steps.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; names the AskUserQuestion tool; mentions 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 rules/nauro-ai/nauro/nauro-loop
Clone the repo
git clone --depth 1 https://github.com/Nauro-AI/nauro

Made for: Cursor.

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 nauro-loop

README.md
[![agentmods](https://agentmods.dev/badge/rules/nauro-ai/nauro/nauro-loop.svg)](https://agentmods.dev/rules/nauro-ai/nauro/nauro-loop)
Your own site
<a href="https://agentmods.dev/rules/nauro-ai/nauro/nauro-loop"><img src="https://agentmods.dev/badge/rules/nauro-ai/nauro/nauro-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 180 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,779 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 5.1 $0.00180 $0.04779
Opus 5 $0.00090 $0.02389
Sonnet 5 $0.00036 $0.00956
Haiku 4.5 $0.00018 $0.00478

Measured 6d ago against content hash 9d7d894b4935, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

nauro-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 6d 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.

.cursor/rules/nauro-loop.mdc · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nauro loop skill

Run gated work origination and coordinate selected Program Delivery. The Program state machine is FRAME -> CHOOSE -> START -> ADVISE -> VERIFY -> ADVANCE. The coordinator owns the verified frame, sequence, handoff, advisory review, integration verification, and next recommendation. It does not implement, approve, file project truth, push, create a pull request, merge, or start the next slice.

User-named work enters as HUMAN-SELECTED. Agent-originated work keeps read-only ORIENT, 1-3 ranked Delivery and Interview candidates, mandatory SELECT, reject all, and no auto-pick path. Interview remains explicit, separate, and non-authoritative. Synchronous non-program Delivery stays outside the Program state machine and keeps the current nauro-ship-task chain.

Authority boundary

These are authority rules. MCP or shell write paths may exist, but they do not grant the coordinator authority to use them for Program Delivery.

  • The loop cannot automatically change project truth or file decisions. Ordinary prompts, Interview results, Delivery handoffs, and program handbacks create no automatic store artifacts. The scheduled ORIENT selection-checkpoint writes are the narrow exception: they create only the existing SELECT checkpoint and pointer through the filesystem and nauro sync mechanism defined below. A selected Interview returns candidate shared understanding only. After the interview, an explicitly approved propose_decision, update_state, or flag_question payload may be executed through /nauro-interview according to its contract and separate later approval gates. Those writes belong to the interview contract, not loop authority.
  • The coordinator may inspect pull-request and merge state through read-only channels, including gh pr view or an equivalent authenticated read channel, only when a required PR-backed repository-anchor check needs it. This includes ORIENT, Resume, replacement-coordinator recovery, and VERIFY. Read-only inspection does not grant publication authority. The coordinator never pushes, creates or edits a pull request, merges, or performs another publication mutation. Only the direct-user Delivery task may perform approved publication work through its own gates.
  • The loop is NOT a "keep moving" override of any inner gate. A standing "keep going" or auto-mode directive does not clear the SELECT gate, the plan gate, a tech-lead pause, or the push gate. The loop exists to repeat the gated chain, not to bypass it.
  • SELECT is never auto-picked. Neither entry mode picks for the human, not even when exactly one candidate ranks or when a scheduled continuation has one surviving candidate. The synchronous mode surfaces SELECT in the parent session; the scheduled mode parks a SELECT checkpoint and exits before any gate; the resume continuation surfaces SELECT to the human. No path resolves SELECT without the human.
  • A hidden child, ordinary subagent, generic agent, or persistent Delivery child is not a substitute for a fresh direct-user Delivery task.

Read the full file on GitHub · 164 lines

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. 6d ago First seen · 164 lines · 180 tokens per session scan A 9d7d894b4935

Subscribe to this mod's changes

nauro-loop is a cursor rule published in the GitHub repository Nauro-AI/nauro (10 stars, last pushed today), licensed Apache-2.0. It adds 180 tokens to every session and 4,779 once invoked, about $0.0009 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.