advisor-build

advisor-build is a command for Claude Code from AI-Native-Systems/north-star-advisor. It costs 17 tokens per session (7,656 once invoked), scanned A, original, MIT.

A command for researching a subject and producing strategic documents from the findings. It uses the North Star methodology and configurable document templates.

In plain words
What is it for?
Creating strategic documents, selecting research depth, and enabling optional user-experience or architecture templates.
Why use it?
It combines research with document generation so strategy materials are based on gathered information. It also checks that the required template source can be found before continuing.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

Part of the northstar plugin — 6 commands shipped together

Good fit Creating strategic documents, selecting research depth, and enabling optional user-experience or architecture templates.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ai-native-systems/north-star-advisor/advisor-build
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.

Clone the repo
git clone --depth 1 https://github.com/AI-Native-Systems/north-star-advisor

Made for: Claude Code.

Or install northstar, the plugin that ships this one along with the rest of its 6 commands.

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 advisor-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/ai-native-systems/north-star-advisor/advisor-build.svg)](https://agentmods.dev/commands/ai-native-systems/north-star-advisor/advisor-build)
Your own site
<a href="https://agentmods.dev/commands/ai-native-systems/north-star-advisor/advisor-build"><img src="https://agentmods.dev/badge/commands/ai-native-systems/north-star-advisor/advisor-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00017 $0.07656
Opus 5 $0.00009 $0.03828
Sonnet 5 $0.00003 $0.01531
Haiku 4.5 $0.00002 $0.00766

Measured 8d ago against content hash cf8173362e82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

advisor-build 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.

commands/advisor-build.md · 996 lines

How it starts

The opening of the file, as written. The whole thing — 996 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/northstar:advisor-build

Research and generate strategic documents following the North Star methodology. This command first conducts domain research, then generates documents informed by the research findings.

Template Source of Truth: templates/index.yml defines all templates, phases, output paths, and dependencies.

To find it:

  1. Check state.json for plugin_index_path (cached location)
  2. If not found, use Glob: **/northstar/**/templates/index.yml
    • If exactly 1 match: update state.json with found path
    • If 0 matches: display "Could not locate templates/index.yml from cached state or fallback glob." and stop
    • If multiple matches:
      • List all found paths
      • Use AskUserQuestion with each path as an option
      • Stop and wait for the user's selection
      • Store selected path in state.json as plugin_index_path
      • Then continue

Arguments

/northstar:advisor-build [options]
Option Description
--ux Add UX design templates (4 templates). Updates state.json.
--deep Add deep architecture templates (7 templates). Updates state.json.
--full Enable all templates (--ux + --deep). Updates state.json.
--search-tool <tool> Override search tool. Updates state.json.
--from <N> Start from phase N (research runs if not cached)
--to <N> Stop at phase N
--only <N> Regenerate only phase N (research runs if not cached)

Prerequisites

  • Project must be initialized with /northstar:advisor
  • north-star-advisor/.work-in-progress/state.json must exist with understanding_verified: true
  • north-star-advisor/.work-in-progress/inputs.yml must contain required inputs

Step 0: Initialize and Confirm

This step is REQUIRED before any generation.

0.1 Load Project State (FIRST)

1. Read north-star-advisor/.work-in-progress/state.json
2. **Legacy state check:** If state.json contains `completed_phases` (pre-2.0.0 format):
   - Display: "This project uses v1.x state format. Run /northstar:resume to migrate or start fresh."
   - Stop generation. Do NOT proceed.
3. Get plugin_index_path from state.json
4. Read north-star-advisor/.work-in-progress/inputs.yml
5. Get current flags: ux, deep, search_tool
6. Get completed_templates array

Read the full file on GitHub · 996 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. 8d ago First seen · 996 lines · 17 tokens per session scan A cf8173362e82

Subscribe to this mod's changes

advisor-build is a command published in the GitHub repository AI-Native-Systems/north-star-advisor (7 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 7,656 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 2026-08-31.