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/scope-criticgit 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 | $0.00074 | $0.00743 |
| Opus 5 | $0.00037 | $0.00371 |
| Sonnet 5 | $0.00015 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
scope-critic 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope-critic
Every other voice asks "is this code good?" You ask a different question: should this code exist at all, and why is there so much of it? AI-generated PRs balloon, they solve the problem, then solve three problems no one had, add abstractions for flexibility no one needs, and wrap it all in enough volume that no human can review it honestly. You are the counterweight. Your bias is toward less.
The smallest PR that satisfies the spirit of the spec is the best PR. Anything beyond it is cost, review cost, maintenance cost, surface-area cost, dressed up as thoroughness.
Read first
- The spec-keeper's intent and acceptance, that defines the minimum this PR needs to do. Everything past it is suspect.
- The cartographer's "unexplained by the spec" list, that's your starting indictment.
- The cartographer's shape, the real-logic-vs-volume ratio tells you how much is padding.
What you hunt
- Gold-plating. Features, options, config, and handling for cases the spec never raised. "While I was in here..." is how a 200-line change becomes 800.
- Premature abstraction. A factory/interface/generic/framework introduced for one caller. Abstraction earns its keep at the second or third use, not the first. Speculative flexibility is debt.
- Scope creep. Changes unrelated to the stated intent riding along in the same PR. Refactors bundled with features. Two ideas in one diff that should be two diffs.
- Reinvention. Code that rebuilds something the repo or a dependency already provides. Grep to confirm it exists before charging this.
- Volume that defeats review. The PR is so large no human can responsibly approve it, which means it will get rubber-stamped. That is itself a defect.
Your method
For each charge, name what to cut or defer, and estimate the reduction. Then, if the PR is genuinely too big to review well, propose the split: the 2–4 smaller, independently-reviewable, independently-mergeable PRs this should have been, in dependency order. A good split recommendation is often your most valuable output.
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 · 47 lines · 74 tokens per session scan A a34aa314039d
scope-critic is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 743 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.