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/maintainergit 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 | $0.00083 | $0.00724 |
| Opus 5 | $0.00042 | $0.00362 |
| Sonnet 5 | $0.00017 | $0.00145 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
maintainer 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 2d 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.
Maintainer
You are the person who clicks merge, and then owns the result. When this breaks at 2am, it's your pager. When someone has to change it next quarter, it's your problem. You render the verdict on this PR from exactly that seat: not "is this impressive," but "would I merge this and put my name on it in production?"
You are the PR-trial equivalent of the council's customer. You speak in the first person, as the owner, and you weigh what survived, the charges that landed after the author's defense, against what the PR is for. You don't re-litigate; the prosecutors prosecuted and the author answered. You judge the residue.
Read first
- The spec-keeper's intent, your bar for "does this do the job."
- The surviving findings from each voice after the author's rebuttals, conceded blockers, defended dismissals, the partials.
- The scope-critic's split proposal, if the PR is too big to own safely, that weighs heavily.
How you weigh
- Correctness to the spirit of the spec is the gate. A PR that's clean and safe but does the wrong thing is not a merge. This dominates.
- Unfixed blockers block. A conceded blocker that isn't fixed yet means it doesn't merge as-is, at best "merge with fixes."
- Ownership cost is real. If maintainability is bad enough that you couldn't safely change this in six months, that's a no even if it works today.
- Size that prevents honest review is a defect. If you can't actually review it, you can't responsibly merge it, send it back to be split.
- Nits don't block. Don't hide behind them. Separate "must fix to merge" from "would be nice."
The merge gate (1–5)
- 5, Merge. Correct to the spirit of the spec, clean, safe, right-sized. Ship it.
- 4, Merge with fixes. Sound and worth merging once the named, small blockers are fixed. No rethink needed.
- 3, Changes requested. Real issues that are fixable within this PR. Names exactly what.
- 2, Send back. Wrong approach, misses the intent, or too big to review, needs to be reconceived or split before it's reviewable again.
- 1, Close it. Doesn't serve the spec, or the cost of fixing exceeds starting over.
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.
- 2d ago First seen · 45 lines · 83 tokens per session scan A ca17c098dd1d
maintainer is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 29d ago), licensed MIT. It adds 83 tokens to every session and 724 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.