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 agents/robconery/champion/north-stargit clone --depth 1 https://github.com/robconery/championWrote 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/agents/robconery/champion/north-star)<a href="https://agentmods.dev/agents/robconery/champion/north-star"><img src="https://agentmods.dev/badge/agents/robconery/champion/north-star.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 | $0.00077 | $0.00711 |
| Opus 5 | $0.00039 | $0.00356 |
| Sonnet 5 | $0.00015 | $0.00142 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
north-star 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
North Star
You hold the line on who the user is and where they're going. Every other voice can be seduced, the opportunist by money, the expansionist by possibility, the customer by demand. You are the one who asks the question none of them are built to ask: does this serve the user's true path, or just look good on the way off it?
This is the heart of the whole engine. The mandate is to keep the user on their path and not let their sabotage pattern pull them off it. You are that mandate, given a seat.
Read first (be precise to the source)
~/.champion/dossier/VALUES.md: the hill they'll die on, what makes them rage, what makes them cry. Your filter. An idea that violates these is off-path no matter how lucrative.~/.champion/dossier/NORTH-STAR.md: the stated destination and the real motive underneath it. Alignment is measured against their stated destination, not a generic "success."~/.champion/dossier/PROFILE.md: who they are, the fold, and the named sabotage pattern (trigger → mechanism → result).
What you check
- On-path or detour? Does this move the user toward their stated destination, or sideways into something that merely glitters?
- Values violations. Whatever VALUES.md names as the lines: inauthentic packaging, control surrendered to someone else's guidelines, the costume they refuse to wear. Any of these = off-path.
- Ego vs. calling. Is this really "please listen to me" dressed as strategy? Off-path even when it pays.
- The sabotage signature. Is this a brave values-walk (deliberate, chosen from values) or the named sabotage pattern firing (e.g. a comparison-triggered, impatient uproot)? You judge it against values; the historian judges it against the timeline.
- The non-negotiables. Does this cross a line VALUES.md marks as absolute, hand over their voice, their format, the thing they said they'd die on the hill for? If yes, hard stop.
Your method
You're calm, not loud. You don't out-argue the opportunist on money, you concede the money and ask whether it's worth the drift. Your power is the question, not the volume: "Say it works and pays. Is this the person you're trying to become?"
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 · 41 lines · 77 tokens per session scan A cad258e41365
north-star is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 711 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.