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 skills add miltonian/cartographer --skill review-prgit clone --depth 1 https://github.com/miltonian/cartographerWrote 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/skills/miltonian/cartographer/review-pr)<a href="https://agentmods.dev/skills/miltonian/cartographer/review-pr"><img src="https://agentmods.dev/badge/skills/miltonian/cartographer/review-pr/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.
<a href="https://agentmods.dev/skills/miltonian/cartographer/review-pr"><img src="https://agentmods.dev/badge/skills/miltonian/cartographer/review-pr.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00049 | $0.00942 |
| Opus 5 | $0.00024 | $0.00471 |
| Sonnet 5 | $0.00010 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
review-pr 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 10d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review on Cartographer Map
Overlay a pull request onto the existing world-model so the user can spatially understand what the PR changes and what it affects.
Prerequisite: The codebase must already have a world-model. If
cartographer_get_summary returns 0 entities, tell the user to run
/cartographer analyze first.
Steps
1. Set project
Call cartographer_set_project with the project root path.
2. Get the PR diff
Use $ARGUMENTS as the PR identifier (number, branch name, or URL).
gh pr diff $ARGUMENTS --name-only
This gives you the list of changed files. If the user didn't provide a PR number, check if there's a current branch with an open PR:
gh pr view --json number,title,headRefName
3. Read the diff details
For each changed file (or the most important ones if there are many):
gh pr diff $ARGUMENTS
Understand what actually changed — not just which files, but what the changes DO.
4. Match changes to world-model entities
Call cartographer_query to find entities in the model. Match by:
- Entity names that correspond to changed functions/components
- Evidence anchors that reference the changed file paths
- Relationships involving changed entities
If a changed file doesn't match any entity in the model, note it — the model may need updating.
5. Determine review order
Order the affected entities from primary change to downstream impact:
- Core change — the main entity the PR modifies (what the PR is "about")
- Supporting changes — entities that changed to support the core
- Affected consumers — entities that read/invoke the changed ones (blast radius)
6. Create the PR changeset
Use kind: "changeset" and changeType on each step so the map renders
change-type indicators (green=added, amber=modified, red=removed, gray=affected).
cartographer_write_slice(
name: "PR #123: Add auth middleware",
description: "Adds authentication checks before write operations",
kind: "changeset",
steps: [
{ entityId: "capability:requireAuth", changeType: "added", label: "new auth middleware" },
{ entityId: "capability:registerTools", changeType: "modified", label: "added auth check before handler" },
{ entityId: "entity:WorldModelStore", changeType: "affected", label: "writes now require auth" },
{ entityId: "capability:broadcast", changeType: "affected", label: "receives only authed writes" }
],
evidence: {
anchors: [{ filePath: "...", lineStart: ..., lineEnd: ..., snippet: "..." }],
confidence: "proven",
provenance: "deterministic",
reasoning: "Matched from git diff"
}
)
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.
- 10d ago First seen · 114 lines · 49 tokens per session scan A 234d6632ca40
review-pr is a skill published in the GitHub repository miltonian/cartographer (1 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 942 once invoked, about $0.0002 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 skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
goal-plan-clean
A guide for creating a reusable plan-review loop. It repeatedly checks a plan, fixes blocking issues and suggestions, and stops after approval or a small number of review rounds.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.
create-task
This skill should be used when creating a task in the active tracker - "create task", "create issue", "bd create", "new task", "add task", "add issue". Ensures all required fields are provided, enforces English-only task content, and suggests epic labels. Triggers on any task creation in any context - commands…