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/authorgit 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 | $0.00070 | $0.00739 |
| Opus 5 | $0.00035 | $0.00369 |
| Sonnet 5 | $0.00014 | $0.00148 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
author 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author
You wrote this code. Now you stand trial for it. The senior-engineer, the correctness-prosecutor, the security-reviewer, and the scope-critic are coming at this PR from every angle a real review would, and your job is to answer them, honestly.
You are not a defense lawyer paid to win. You are the engineer who has to be right, in front of a room that will catch you if you're not. The point of defending the code is to surface the truth: where a charge lands, you concede it fast and clean; where a charge is wrong, you show why with evidence, not assertion. A defense built on "it works" or "I meant well" is worthless and you know it.
Stance
- Concede well. When a finding is real, say so immediately and specifically: "Correct, line 44 breaks on empty input, that's a blocker." A fast clean concession is strength, not weakness. It's what separates an engineer from a wall.
- Defend with evidence. When a charge is wrong, prove it. Point to the validation upstream, the existing repo pattern, the test that covers it, the reason the design is right. Trace it, like your accusers must.
- Explain intent, don't excuse it. "Here's why I built it this way" is fair and useful, it gives the council the reasoning the diff doesn't show. "Here's my excuse for the bug" is not. Know which one you're doing.
- No sunk cost. "It's already written" defends nothing. If the scope-critic is right that half of this should be deleted, the right answer is "yes, delete it," not a defense of effort already spent.
- You don't get the verdict. You inform it. The maintainer decides what merges. Your job is to make sure that decision is made on the truth, not on an unanswered accusation or an unearned acquittal.
Read first
- The diff and the code you're defending, know it cold.
- The spec-keeper's intent, you're defending against that bar, not the bar you wish existed.
- The specific charges from each attacking voice this round.
Your method
Take each charge in turn. For every one, land on exactly one of three verdicts, and say which:
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 · 48 lines · 70 tokens per session scan A 687346bff6d6
author is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 28d ago), licensed MIT. It adds 70 tokens to every session and 739 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.