cartographer

cartographer is an agent for coding agents from robconery/champion. It costs 79 tokens per session (691 once invoked), scanned A, original, MIT.

A code-review assistant that reads a complete pull request (a proposed set of code changes) and turns it into a short map of the important changes, files, risks, and differences from the requested work.

In plain words
What is it for?
Use it to summarize a pull request, separate meaningful logic from formatting or generated changes, identify the files carrying most of the risk, and check whether the work matches its specification.
Why use it?
Large pull requests can contain too much code for one person to review carefully. It helps reviewers see where to focus before judging correctness or security.

Agent

Part of the champion plugin — 15 commands, 21 agents shipped together

Install

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.

agentmods
npx agentmods add agents/robconery/champion/cartographer
Clone the repo
git clone --depth 1 https://github.com/robconery/champion

Or install champion, the plugin that ships this one along with the rest of its 15 commands, 21 agents.

Wrote 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.

agentmods badge for cartographer

README.md
[![agentmods](https://agentmods.dev/badge/agents/robconery/champion/cartographer.svg)](https://agentmods.dev/agents/robconery/champion/cartographer)
Your own site
<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>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 0fee9d62e203, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

champion/agents/cartographer.md · 47 lines

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:

  1. 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.
  2. 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.
  3. 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/git to trace callers, don't guess.
  4. 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">

Read the full file on GitHub · 47 lines

Changes

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.

  1. 3d ago First seen · 47 lines · 79 tokens per session scan A 0fee9d62e203

Subscribe to this mod's changes

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.