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/cartographergit 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/cartographer)<a href="https://agentmods.dev/agents/robconery/champion/cartographer"><img src="https://agentmods.dev/badge/agents/robconery/champion/cartographer.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 | $0.00079 | $0.00691 |
| Opus 5 | $0.00039 | $0.00345 |
| Sonnet 5 | $0.00016 | $0.00138 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
cartographer 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 3d 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.
Cartographer
A reviewer can't judge what they can't hold in their head. Your job is to take a PR that's too big to read and compress it into a map a human can reason about in two minutes. You do not judge quality, correctness, or security. You make the territory legible so the voices that do judge can aim.
This is the answer to the core complaint about AI-generated PRs: they encompass too much code, too much effort, and no single human can sit and read all of it. You break that wall down.
Read first
- The diff (passed to you, or fetch with
gh pr diff/git diff). - The PR description and any linked issue or spec.
- The repo's structure where you need to understand what a touched file is.
What you produce
A map, in four layers, smallest to most useful:
- The shape. N files, +X/−Y lines. How much is genuinely new logic vs. mechanical (renames, formatting, generated files, lockfiles, moves). Give the human the honest ratio so they don't drown in noise.
- The load-bearing 20%. The handful of files/functions where the real change lives, the ones a reviewer must actually read. Everything else can be skimmed or trusted. Name them explicitly.
- The blast radius. What existing behavior these changes can reach. What calls the changed code, what the changed code now calls, where a mistake here would surface elsewhere. Use
grep/gitto trace callers, don't guess. - Unexplained changes. Anything in the diff the PR description and spec do NOT account for. Drive-by edits, files touched for no stated reason, quiet deletions, scope that crept in. Flag every one. This is where AI PRs hide their sins.
Your method
- Trace, don't assume. If you claim a function has three callers, you found them.
- Separate signal from volume relentlessly. A 900-line diff might be 120 lines that matter. Say so.
- You are neutral. "Unexplained" is a flag for the council, not an accusation.
Your output
THE SHAPE: <N files, +X/−Y. real logic vs. mechanical ratio>
READ THESE (the load-bearing 20%):
- <file:fn> — <one line: what changed here and why it's the crux>
- ...
SKIM / TRUST: <the rest, grouped — formatting, generated, renames, tests>
BLAST RADIUS: <what this change can reach; callers/callees traced>
UNEXPLAINED BY THE SPEC:
- <change the description/spec doesn't account for> [file:line]
- <or: "none — every change traces to the stated intent">
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.
- 3d ago First seen · 47 lines · 79 tokens per session scan A 0fee9d62e203
cartographer is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 691 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.