inspect

inspect is a skill for Claude Code from miltonian/cartographer. It costs 38 tokens per session (339 once invoked), scanned A, original, MIT.

A codebase-questioning guide that uses a stored world-model, a searchable record of project entities and their relationships.

In plain words
What is it for?
It is for finding what calls what, understanding system boundaries, tracing relationships, and checking side effects in analyzed projects.
Why use it?
It helps answer how code works without starting from scratch, while showing evidence and gaps in what has been recorded.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the cartographer plugin — 5 skills, 1 command, 1 agent, 1 hook, 1 MCP server 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 skills/miltonian/cartographer/inspect
Any agent
npx skills add miltonian/cartographer --skill inspect
Clone the repo
git clone --depth 1 https://github.com/miltonian/cartographer

Made for: Claude Code.

Or install cartographer, the plugin that ships this one along with the rest of its 5 skills, 1 command, 1 agent, 1 hook, 1 MCP server.

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 inspect

README.md
[![agentmods](https://agentmods.dev/badge/skills/miltonian/cartographer/inspect.svg)](https://agentmods.dev/skills/miltonian/cartographer/inspect)
Your own site
<a href="https://agentmods.dev/skills/miltonian/cartographer/inspect"><img src="https://agentmods.dev/badge/skills/miltonian/cartographer/inspect.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 339 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 5.1 $0.00038 $0.00339
Opus 5 $0.00019 $0.00169
Sonnet 5 $0.00008 $0.00068
Haiku 4.5 $0.00004 $0.00034

Measured 6d ago against content hash a3f8bda1e13a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

inspect 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.

plugin/skills/inspect/SKILL.md · 36 lines

What it actually says

Inspect World-Model

You have access to Cartographer's stored world-model. Use it to answer questions about the codebase with evidence-grounded responses.

Available MCP Tools

  • cartographer_query — Search for entities/relationships by kind, name, or involvement
  • cartographer_get_entity — Get full details including evidence and relationships
  • cartographer_get_summary — See what's in the model

How to Answer Questions

  1. Query first — check cartographer_query or cartographer_get_entity before reading source
  2. Cite evidence — when the model has source anchors, cite file:line in your answer
  3. Flag gaps — if the model doesn't have what's needed, say so and offer to analyze further
  4. Separate proven from inferred — tell the user which parts are proven vs inferred

Example Questions

  • "What calls the payment handler?" → query relationships involving that entity
  • "What are the main boundaries?" → query entities of kind boundary
  • "How does auth work?" → get the auth boundary entity, then its relationships
  • "What side effects does checkout have?" → query side-effect entities related to checkout

When the Model Is Empty

If cartographer_get_summary shows 0 entities, suggest the user run /cartographer analyze first to populate the world-model.

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 · 36 lines · 38 tokens per session scan A a3f8bda1e13a

Subscribe to this mod's changes

inspect is a skill published in the GitHub repository miltonian/cartographer (1 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 339 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.