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.
npx agentmods add commands/ai-native-systems/north-star-advisor/helpgit clone --depth 1 https://github.com/AI-Native-Systems/north-star-advisorWrote 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/commands/ai-native-systems/north-star-advisor/help)<a href="https://agentmods.dev/commands/ai-native-systems/north-star-advisor/help"><img src="https://agentmods.dev/badge/commands/ai-native-systems/north-star-advisor/help.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 | $0.00007 | $0.00984 |
| Opus 5 | $0.00003 | $0.00492 |
| Sonnet 5 | $0.00001 | $0.00197 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
help 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 4d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/northstar:help
Display available North Star Advisor commands and usage information.
Usage
/northstar:help
Output
Display the following help information:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
NORTH STAR ADVISOR
Strategic Document Generation for Agentic Applications
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
COMMANDS
/northstar:advisor [flags]
Begin strategic discovery through open exploration.
Acts as your thinking partner to articulate what you're building.
Flags:
--ux Include UX design templates (USER_JOURNEYS, UI_DESIGN_SYSTEM, ACCESSIBILITY, etc.)
--deep Include deep architecture templates (PIPELINE, RESILIENCE, OBSERVABILITY, etc.)
--full Include all 23 templates (equivalent to --ux --deep)
/northstar:advisor-build [options]
Research and generate strategic documents.
Runs domain research, then generates documents.
Options:
--from <N> Start from phase N
--to <N> Stop at phase N
--only <N> Regenerate only phase N
Note: phase numbers come from templates/index.yml
--ux Add UX templates (can extend existing project)
--deep Add deep architecture templates
--full Add all templates (equivalent to --ux --deep)
/northstar:status
Show current progress (research, generation phases).
/northstar:resume [options]
Resume from the last checkpoint.
Options:
--restart Restart current template from scratch
--rollback Go back to previous template
/northstar:export [options]
Package docs and ai-context.yml into a shareable zip.
Options:
--output <path> Custom output path
/northstar:help
Show this help message.
WORKFLOW
1. /northstar:advisor
- Open exploration: "What are you building, and why?"
- Follow-up questions until concrete understanding
- Understanding checkpoint
- Saves: discovery.md, inputs.yml, ai-context.yml
2. /northstar:advisor-build
- Research phase: 5 parallel agents (tech, features, arch, pitfalls, intelligence layer)
- Research checkpoint
- Generate strategic documents
- Research informs phases 6, 7, 7d, 8
RESEARCH PHASE
Before generation, 5 research agents run in parallel:
- Tech Stack: Frameworks, libraries, best practices
- Features & UX: Expected features, UX patterns
- Architecture: Patterns, data flow, scalability
- Pitfalls: Common mistakes, security concerns
- Intelligence Layer: Embedding models, RAG patterns, model routing, evaluation
Research is cached for 24 hours.
GENERATION PHASES (see templates/index.yml for authoritative list)
Core templates (always generated):
Phases 1-4: Strategy & positioning
Phases 6-13: Architecture & implementation
UX templates (--ux flag):
Phase 5a-5d: Design system, accessibility & wireframes
Deep templates (--deep flag):
Phase 7d: Advanced architecture patterns
Counts: 12 core + 4 ux + 7 deep = 23 total (+ ai-context.yml)
OUTPUT STRUCTURE
north-star-advisor/
├── ai-context.yml Strategic context for Claude Code
├── .work-in-progress/ Working state (hidden)
│ ├── state.json Generation progress
│ ├── inputs.yml User inputs
│ ├── discovery.md Exploration notes
│ └── research/ Cached research
└── docs/ Generated strategic documents
Use /northstar:resume to continue after interruption.
Use /northstar:export to create a shareable zip.
EXAMPLES
# Start strategic discovery
/northstar:advisor --ux
# Research and generate all documents
/northstar:advisor-build
# Generate only the architecture phase
/northstar:advisor-build --only 6
# Add UX and deep templates after initial build
/northstar:advisor-build --full
# Check progress
/northstar:status
# Export for sharing
/northstar:export
MORE INFO
Documentation: https://github.com/AI-Native-Systems/north-star-advisor
Author: Patrick Pena / AI Native Systems™
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.
- 4d ago First seen · 144 lines · 7 tokens per session scan A fe588027d506
help is a command published in the GitHub repository AI-Native-Systems/north-star-advisor (7 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 984 once invoked, about $0.0000 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 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.
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.
adr
Generate a well-formed Architecture Decision Record from a change in context — Status / Context / Decision / Consequences. One-shot helper, off-spine.
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.
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.
init
Install the formatters this repository needs, with every command visible before it runs.