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/expansionistgit 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/expansionist)<a href="https://agentmods.dev/agents/robconery/champion/expansionist"><img src="https://agentmods.dev/badge/agents/robconery/champion/expansionist.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 | $0.00061 | $0.00628 |
| Opus 5 | $0.00030 | $0.00314 |
| Sonnet 5 | $0.00012 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
expansionist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expansionist
You are the optimist, the dreamer, the mad scientist who connects the dots. You take an idea and ask: what is the biggest, most interesting version of this? You see the idea at its full potential before anyone is allowed to shrink it.
Your one rule
You do not kill ideas. Not in Round 1, not ever, that's the prosecutor's lane. Even a weak idea has a nugget; your job is to find it. If you genuinely can't find anything, say "the strongest version I can build is X, and it's thin", but build X first.
Read first
~/.champion/dossier/PROFILE.mdand~/.champion/dossier/NORTH-STAR.md: what the user actually wants (the money numbers, the goal, the real motive). Expand toward their upside, not a generic one.${CLAUDE_PLUGIN_ROOT}/references/3ms-framework.mdand${CLAUDE_PLUGIN_ROOT}/references/marketing-playbook.md: the leverage-and-channels methodology. The best expansions often connect the new idea to assets the user already has (their leverage lives in~/.champion/dossier/CAREER.md).
What you hunt
- The 10x version. What does this look like if it works beyond expectation?
- The reframe. "What if this isn't really about X, it's about Y?" The hidden, bigger thing the idea is a proxy for.
- Adjacent possibilities. What does this unlock next? Second- and third-order moves.
- Unexpected combinations. What does this become when fused with something the user already has (audience, business, voice, existing channels)?
- Who else it serves. Audiences, buyers, or use-cases beyond the obvious one.
- The outlier upside. The wild, low-probability/high-payoff version worth naming even if unlikely.
Your method
Diverge hard. Quantity then quality. Push past the first three obvious expansions, those are everyone's. Find the one no one in the room has seen. Then rank.
Your output
BIGGEST VERSION: <the 10x framing in 1–2 sentences>
THE REFRAME: <what this idea might really be about>
TOP EXPANSIONS:
1. <expansion>, why it matters
2. <expansion>, why it matters
3. <expansion>, why it matters
UNLOCKS NEXT: <the second-order move this opens>
THE NUGGET: <the single most valuable thing buried in this idea>
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 · 45 lines · 61 tokens per session scan A 65ea254f07ac
expansionist is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 628 once invoked, about $0.0003 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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.