agentmods.dev

advisor

advisor is a command for coding agents from AI-Native-Systems/north-star-advisor. It costs 18 tokens per session (3,156 once invoked), scanned A, original, MIT.

A guided command for exploring and defining what you want to build, with optional templates for user experience and software architecture.

In plain words
What is it for?
Starting a North Star Advisor project, choosing design or architecture templates, selecting a research tool, and setting an output folder.
Why use it?
It helps turn an early or unclear idea into a more clearly described project through questions and discussion.

Command

Part of the northstar plugin — 6 commands, 3 agents shipped together

not rated 7 5mo ago A scan 18 tokens original MIT
View the source file AI-Native-Systems/north-star-advisor northstaradvisor.app
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/ai-native-systems/north-star-advisor/advisor
Clone the repo
git clone --depth 1 https://github.com/AI-Native-Systems/north-star-advisor

Or install northstar, the plugin that ships this one along with the rest of its 6 commands, 3 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/ai-native-systems/north-star-advisor/advisor.svg)](https://agentmods.dev/commands/ai-native-systems/north-star-advisor/advisor)
Your own site
<a href="https://agentmods.dev/commands/ai-native-systems/north-star-advisor/advisor"><img src="https://agentmods.dev/badge/commands/ai-native-systems/north-star-advisor/advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,156 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 $0.00018 $0.03156
Opus 5 $0.00009 $0.01578
Sonnet 5 $0.00004 $0.00631
Haiku 4.5 $0.00002 $0.00316

Measured 5d ago against content hash 920896b89d57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

advisor 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 5d 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.md · 406 lines

How it starts

The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/northstar:advisor

Begin strategic discovery for a new North Star Advisor project. This command acts as your thinking partner, helping you articulate what you're building through open exploration and targeted questions.

Arguments

/northstar:advisor [--ux] [--deep] [--full] [--target <path>] [--search-tool <tool>]
Flag Description
--ux Add UX design templates (4 templates). Stored in state.json.
--deep Add deep architecture templates (7 templates). Stored in state.json.
--full Enable all templates (--ux + --deep). Stored in state.json.
--target <path> Specify output directory (default: current directory)
--search-tool <tool> Search tool for research. Stored in state.json.

Template counts: Read templates/index.yml for the authoritative list.

Philosophy

You are a thinking partner, not an interviewer.

Your goal is not to extract information—it's to help the user discover what they actually want to build. Many users haven't fully thought through their ideas. Your questions help them think.

Workflow

Step 1: Check for Existing Project

  1. Check if north-star-advisor/.work-in-progress/state.json exists
  2. If exists:
    • Read current state
    • Legacy state check: If state.json contains completed_phases (pre-2.0.0 format):
      • Display: "This project uses v1.x state format."
      • Ask user:
        • "Run /northstar:resume to migrate" → redirect to /northstar:resume
        • "Start fresh (keeps existing docs)":
          • Delete north-star-advisor/.work-in-progress/ directory
          • Display: "Working state cleared. Existing docs preserved in north-star-advisor/docs/"
          • Proceed to Step 2
      • Do NOT continue into the normal flow below
    • Check if new flags were passed (--ux, --deep, --full)
    • If new flags AND project has completed templates:
      • Ask user: "A North Star project already exists. Would you like to:"
        • Update flags and generate new templates (/northstar:advisor-build with merged flags)
        • Start fresh (overwrites existing)
      • If "update flags", merge flags into state.json and run /northstar:advisor-build
      • If "start fresh":
        • Delete north-star-advisor/.work-in-progress/ directory
        • Proceed to Step 2
    • If no new flags OR no completed templates:
      • Ask user: "A North Star project already exists. Would you like to:"
        • Continue existing project (/northstar:resume)
        • Start fresh (overwrites existing)
      • If "start fresh":
        • Delete north-star-advisor/.work-in-progress/ directory
        • Proceed to Step 2
      • If "continue", redirect to /northstar:resume
  3. If not exists, proceed to Step 2

Read the full file on GitHub · 406 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. 5d ago First seen · 406 lines · 18 tokens per session scan A 920896b89d57

Subscribe to this mod's changes

advisor is a command published in the GitHub repository AI-Native-Systems/north-star-advisor (7 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 3,156 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.

Planningagentic-application-designai-design-engineeringai-engineeringclaude-codeclaude-code-plugin
Related

Other commands, from other repositories

release

Guided release for the skill-engine repo. Bumps the six version surfaces, drafts the CHANGELOG entry, runs validators, then pauses for the maintainer to commit, push, and tag manually. Accepts major / minor / patch / explicit X.Y.Z.

nick-railsback/skill-engine · 53 tokens

godmode

Orient in five lines: where you are, what's done, and the exact next command to run. Reads workflow state and the live skill/agent inventory.

SyloRei/claude-godmode · 34 tokens

adr

Generate a well-formed Architecture Decision Record from a change in context — Status / Context / Decision / Consequences. One-shot helper, off-spine.

SyloRei/claude-godmode · 33 tokens

changelog

Draft a Keep a Changelog–style entry (Added / Changed / Fixed / Removed) from commits since the last tag. Standalone helper — does not replace /ship's release step.

SyloRei/claude-godmode · 41 tokens

pr-describe

Draft a PR description (summary / what changed / test plan) from the branch's commits and diff against the base branch. Off-spine helper, no agents.

SyloRei/claude-godmode · 37 tokens

init

Install the formatters this repository needs, with every command visible before it runs.

azrtydxb/procoder · 16 tokens