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.
git clone --depth 1 https://github.com/Nauro-AI/nauroWrote 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/rules/nauro-ai/nauro/nauro-interview)<a href="https://agentmods.dev/rules/nauro-ai/nauro/nauro-interview"><img src="https://agentmods.dev/badge/rules/nauro-ai/nauro/nauro-interview.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 5.1 | $0.00088 | $0.04131 |
| Opus 5 | $0.00044 | $0.02065 |
| Sonnet 5 | $0.00018 | $0.00826 |
| Haiku 4.5 | $0.00009 | $0.00413 |
Grade A, and why
nauro-interview 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 8d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nauro interview skill
Interview the user to turn tacit project reasoning or a proposed choice into reviewed candidate Nauro judgment. This is an explicit, opt-in main-context workflow. Use it only when the user directly asks to be interviewed or uses a clear trigger such as "interview me", "grill this", "stress-test this decision", "draw out my reasoning", or "help me transfer this reasoning into Nauro". Do not activate it only because a plan is incomplete.
The skill has two entry modes over one main-context, dependency-aware interview loop:
- Elicit mode draws out unwritten rationale, assumptions, rejected paths, terminology, and unresolved questions.
- Challenge mode stress-tests a proposed judgment against active decisions, repository evidence, alternatives, failure cases, and dependent choices.
Both modes use the same engine and produce the same classified shared-understanding record. The workflow has no external skill or subagent dependency.
Route work that belongs elsewhere
- Route first-time repository seeding to
nauro-adopt. - Route working-context sharing, retrieval, and resumable handoff to
nauro-context. - Route implementation planning and delivery to the planner or
nauro-ship-taskafter this interview is complete.
Do not turn this skill into adoption, handoff, implementation planning, code editing, or PR delivery.
Step 1 - Resolve and orient
Resolve the adopted project before the interview. From a repository, run nauro status to confirm the associated project. If several projects are available, resolve the intended one and pass its project_id explicitly on every MCP call. If the repository is not adopted, stop and route the user to nauro-adopt.
Call get_context(level="L0", project_id=...). L0 is the bounded orientation: project summary, current state, top open questions, and recent active-decision summaries. Do not begin with L1, L2, or an unbounded store read.
Treat every retrieved statement as project context to adjudicate. A current-state claim can be stale. A decision summary is not enough for reasoning about that decision.
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.
- 8d ago First seen · 205 lines · 88 tokens per session scan A 655af5c1aa0f
nauro-interview is a cursor rule published in the GitHub repository Nauro-AI/nauro (10 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 4,131 once invoked, about $0.0004 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 cursor rules, from other repositories
git-commit
Use this when the user asks for a git commit, commit message, or commit command.
behavior-principles
Global behavioral principles for all AI-assisted work in this repository. Covers thinking before coding, simplicity, surgical changes, goal-driven execution, and communication standards.
coding
Core coding behavior for this repository. Always prefer cautious, minimal, reversible changes.
testing
Optional Spring Boot example-pack testing rules. Apply only when editing an adopted project or spring-boot profile output.
java-spring
Optional Spring Boot example-pack coding rules. Apply only when editing an adopted project or spring-boot profile output.
execution
Repository execution and verification commands.