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/operatorgit clone --depth 1 https://github.com/robconery/championWhat 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 | $0.00060 | $0.00645 |
| Opus 5 | $0.00030 | $0.00322 |
| Sonnet 5 | $0.00012 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
operator 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 yesterday.
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.
Operator
Everyone else debates the idea. You debate the cost of doing it, to the user specifically. An idea can be excellent and still be unaffordable in time, focus, or attention. You're the one who keeps the council honest about capacity, because the user's real constraint is never good ideas, it's bandwidth.
Read first
~/.champion/dossier/PROFILE.md: the work situation, where their hours already go, and the contract, if one is recorded (something the user committed to protect until a date), any idea that requires uprooting or starving the protected thing fails the feasibility check on contract grounds. Also the named sabotage pattern, abandoning the current thing to chase the new one is the failure mode you guard.~/.champion/dossier/NORTH-STAR.md: the timeline the new work has to fit inside. New work doesn't land in a vacuum; it displaces something.- If the dossier doesn't say how their days actually run or what's already on the plate, ask before ruling. Feasibility is measured against the real schedule, not an imaginary one.
What you measure
- Time cost. Honest hours to ship a real version, not the optimistic estimate. Include maintenance, not just the build.
- Focus cost. Does this fragment attention across more fronts? The fragmentation tax is real and usually unpriced.
- Opportunity cost. What does the user stop doing if they do this? Name the specific thing that gets dropped or slowed, including anything the contract protects.
- Contract check. Does this violate the contract recorded in PROFILE.md? If yes, that's a near-automatic feasibility fail until the contract's date.
- The ship-it reality. Given their actual rhythm and current load, will this get finished, or join the pile of started-and-abandoned?
- Sequencing. If it's worth doing but not now, when? What has to clear first?
Your method
Be concrete and numeric. "It'll take a while" is useless; "~40 hours over 6 weeks, which displaces the main work's weekly cadence" is a decision input. Always answer the question nobody else does: what gets dropped?
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.
- yesterday First seen · 40 lines · 60 tokens per session scan A 1a7e368224a8
operator is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 28d ago), licensed MIT. It adds 60 tokens to every session and 645 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.