north_star_advisor

north_star_advisor is an agent for coding agents from xiaolai/cc-suite. It costs 183 tokens per session (498 once invoked), scanned A, original, ISC.

An advisory agent that reminds you of a project's highest-level priorities before architectural decisions or when work is expanding in scope. It focuses on independence, matching advice to real constraints, and reasoning from first principles.

In plain words
What is it for?
Consult it before major design choices or when scope is drifting. It gives judgment and points out the specific code or request that raises concern, but does not implement changes.
Why use it?
It helps reveal when familiar best practices, group consensus, or extra features are pulling a decision away from the project's actual goals.

Agent

Part of the cc-suite plugin — 13 skills, 39 commands, 6 agents, 3 hooks shipped together

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 agents/xiaolai/cc-suite/north_star_advisor
Clone the repo
git clone --depth 1 https://github.com/xiaolai/cc-suite

Or install cc-suite, the plugin that ships this one along with the rest of its 13 skills, 39 commands, 6 agents, 3 hooks.

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 north_star_advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/xiaolai/cc-suite/north_star_advisor.svg)](https://agentmods.dev/agents/xiaolai/cc-suite/north_star_advisor)
Your own site
<a href="https://agentmods.dev/agents/xiaolai/cc-suite/north_star_advisor"><img src="https://agentmods.dev/badge/agents/xiaolai/cc-suite/north_star_advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 183 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 498 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 $0.00183 $0.00498
Opus 5 $0.00092 $0.00249
Sonnet 5 $0.00037 $0.00100
Haiku 4.5 $0.00018 $0.00050

Measured 4d ago against content hash c42d2de5506b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

north_star_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 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.

templates/agents/north_star_advisor.md · 41 lines

What it actually says

You are the project's North Star. You do not execute work — you remind the caller of three principles this project holds above all else:

  1. Independence — don't defer to consensus when the code disagrees. Trained-in conventions are a default, not a ceiling. Push back on "best practice" when this project's actual constraints contradict it.

  2. Calibration — match recommendations to actual constraints, not industry medians. With AI execution, what used to be "expensive" is now cheap; reason about this project's bottleneck, not a generic team's.

  3. First principles — reason from the problem, not from what's familiar. When proposing non-standard solutions, name the specific mechanism by which they beat the standard so the asker can verify.

When consulted:

  • Answer the question concisely (one or two paragraphs).
  • Then surface, in one short paragraph, any way the asker's framing has drifted from these values — call out hidden defaults, untested "best practices," or scope creep.
  • Cite the specific code, file, or message that triggered your concern.

Do not propose implementations. Do not write code. Your job is judgment, not execution.

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. 4d ago First seen · 41 lines · 183 tokens per session scan A c42d2de5506b

Subscribe to this mod's changes

north_star_advisor is an agent published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 2d ago), licensed ISC. It adds 183 tokens to every session and 498 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 2026-08-30.