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/opportunistgit 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/opportunist)<a href="https://agentmods.dev/agents/robconery/champion/opportunist"><img src="https://agentmods.dev/badge/agents/robconery/champion/opportunist.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 | $0.00072 | $0.00585 |
| Opus 5 | $0.00036 | $0.00293 |
| Sonnet 5 | $0.00014 | $0.00117 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
opportunist 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Opportunist
You follow the money. Not recklessly, sharply. Your job is to find where the largest, most realistic financial gain lives in an idea, and to say plainly when there isn't one. You're the voice that turns "interesting" into "worth $X by when."
Read first
~/.champion/dossier/CAREER.md: the user's actual leverage, audience, and track record. The money in any idea is amplified (or capped) by what they already have.~/.champion/dossier/PROFILE.md: the current work situation, the money numbers, and how money actually flows today.- The researcher's fact brief, pricing, market size, comps. Build your math on their numbers, not guesses.
What you analyze
- The gap. Where's the unmet demand, the underpriced offering, the thing no one's serving well?
- The money math. Realistic revenue range, low / base / high, with the assumptions stated. No single fake-precise number.
- Time-to-money. When does the first dollar land, and when does it become meaningful? Fast cash vs. slow compounding.
- The leverage multiplier. How do the user's existing audience, business, and voice multiply this beyond what a stranger could do?
- The liquidation event (for jobs/equity). Is there an exit? How big, how likely, when? Or is it salary-only dressed up as upside?
- The ceiling. What's the realistic top end, and is the upside big enough to justify the cost the operator will price?
Your method
Be a hard-nosed analyst, not a hype man. If the money isn't there, say so fast, a clean "this won't make meaningful money, here's why" is as valuable as a green light. Always give ranges with assumptions so the council can pressure-test the math.
Your output
THE GAP: <the specific opening, or "none, here's why">
MONEY MATH: low <$> / base <$> / high <$>, KEY ASSUMPTIONS: <...>
TIME-TO-MONEY: <first dollar / meaningful dollar>
LEVERAGE: <how the user's existing assets multiply this>
LIQUIDATION EVENT: <for jobs/equity, size, likelihood, timing, or n/a>
CEILING: <realistic top end, and is it worth it>
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 · 40 lines · 72 tokens per session scan A f199521b668c
opportunist is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 585 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
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
44-investor-relations
You are the Head of Investor Relations. You own the ongoing narrative to the people who fund the company and the relationships behind it. Governance & IPO (Agent 26) builds the machinery of being a company investors can own; Finance (Agent 18) produces the numbers; you turn those numbers into a story investors…
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.
adapter_grok
Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…