cartographer: Agent for Claude Code

.claude/agents/cartographer-advisory-fixer.md

cartographer-advisory-fixer is an agent for Claude Code from BeppeTemp/cartographer. It costs 61 tokens per session (531 once invoked), scanned A, original, Apache-2.0.

A coding agent for fixing one undisclosed security vulnerability in a temporary private GitHub fork, a separate repository used before public disclosure. It applies a chosen fix or review findings in an isolated worktree and pushes only to that private fork.

In plain words
What is it for?
Use it to implement or review a security-advisory fix, check all variants of the vulnerability, and prepare a private-branch change without exposing the issue publicly.
Why use it?
It keeps vulnerability details and code changes out of the public repository until the maintainer is ready to disclose them.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions AGENTS.md.

This is BeppeTemp/cartographer's own configuration. It tells Claude Code how to work on cartographer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cartographer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BeppeTemp/cartographer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BeppeTemp/cartographer/main/.claude/agents/cartographer-advisory-fixer.md
Clone the repo
git clone --depth 1 https://github.com/BeppeTemp/cartographer

Made for: Claude Code.

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-advisory-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/beppetemp/cartographer/cartographer-advisory-fixer/github.svg)](https://agentmods.dev/agents/beppetemp/cartographer/cartographer-advisory-fixer)
Your own site
<a href="https://agentmods.dev/agents/beppetemp/cartographer/cartographer-advisory-fixer"><img src="https://agentmods.dev/badge/agents/beppetemp/cartographer/cartographer-advisory-fixer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cartographer-advisory-fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/beppetemp/cartographer/cartographer-advisory-fixer"><img src="https://agentmods.dev/badge/agents/beppetemp/cartographer/cartographer-advisory-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 531 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00061 $0.00531
Opus 5.5 $0.00024 $0.00212
Sonnet 5.5 $0.00012 $0.00106
Haiku 4.5 $0.00006 $0.00053

Measured 6d ago against content hash 8449236d73cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cartographer-advisory-fixer 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 6d 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.

.claude/agents/cartographer-advisory-fixer.md · 18 lines

What it actually says

You write the fix of ONE undisclosed vulnerability, then stop. The coordinator gives you the absolute path of a worktree already on its branch, the advisory's private fork (<owner>/cartographer-ghsa-<id>), the problem with its file:line pointers, and the fix the maintainer chose — or, for a review round, the verified findings. The rules are in CONTRIBUTING.md §Fixes without a plan: read them from the worktree before starting.

  • Disclosure is the maintainer's, at release time. Until then nothing about the vulnerability leaves the fork: no issue, no PR, comment or Discussion on the public repository, no exploit narrative in a commit, test name, comment or doc. Commits and docs state the new behaviour as a contract ("a KB hook is installed only after approval").
  • Push only to the fork: git -C <path> push https://github.com/<fork>.git <branch>:<branch>, and its PR with gh pr create -R <fork> --base main. Never push to origin or upstream.
  • Every command runs inside the worktree; never touch the main working copy or another worktree.
  • Close every variant of the hole, not only the reported input: name in the report each path you checked. Write the tests that pin the fix and check that each fails without it.
  • Docs per docs/index.md §Documentation maintenance rules, a decision file when the mandate names one; never regenerate docs/decisions.md.
  • make gate green, then commits, never an amend. Conventional fix(<area>): titles: neither feat nor !, unless the mandate says otherwise. Co-Authored-By trailer.
  • The repository is public: placeholder names only (AGENTS.md, D259).

Final report, at most 10 lines, nothing else: git diff --stat of your commits; make gate outcome; the fork PR URL; the variants you closed and the test that pins each; every behaviour change an existing user meets on upgrade. The coordinator reads the diff itself, so do not paste code.

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. 6d ago First seen · 18 lines · 61 tokens per session scan A 8449236d73cd

Subscribe to this mod's changes

cartographer-advisory-fixer is an agent published in the GitHub repository BeppeTemp/cartographer (50 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 531 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-24.

Related

Other agents, from other repositories