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 skills/miltonian/cartographer/explorenpx skills add miltonian/cartographer --skill exploregit 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/explore)<a href="https://agentmods.dev/skills/miltonian/cartographer/explore"><img src="https://agentmods.dev/badge/skills/miltonian/cartographer/explore.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 | $0.00053 | $0.00617 |
| Opus 5 | $0.00026 | $0.00309 |
| Sonnet 5 | $0.00011 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
explore 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Exploration
Verify tools work: call cartographer_get_summary. If it fails, stop and
tell the user the Cartographer MCP tools are not connected.
Set the project root: cartographer_set_project.
Save a snapshot: cartographer_snapshot with label "pre-exploration".
Checklist
Copy this checklist. Track progress. Do not skip items.
Exploration Progress:
- [ ] Orient: read project, understand what it does
- [ ] Behaviors: trace key behaviors end-to-end as slices (as many as the system warrants)
- [ ] Boundaries: cluster entities by concern, record boundaries
- [ ] Depth: create sub-boundaries (check_depth must pass)
- [ ] Perspectives: create at least one focused perspective
- [ ] Synthesis: report findings to user
How to Explore
Behaviors first. Identify what the system DOES, not what files it has. Trace each behavior from entry point to completion. Record entities as encountered: actors, capabilities, state, side effects, invariants, failure points. Record each path as a behavior slice.
Boundaries emerge from behaviors. After tracing flows, cluster entities that participate in the same behaviors. Name by concern ("authentication", "payment processing"), NEVER by directory ("src", "lib", "components").
Depth is mandatory. Every boundary with more than 3 entities must have sub-boundaries. Read the source for the key classes/functions inside each boundary. Create a child boundary. Record its internal capabilities, state, invariants as children.
Perspectives for navigation. Create at least one perspective for the
most important concern. If cartographer_create_perspective is unavailable,
skip gracefully — sub-boundaries and slices provide depth regardless.
Before Finishing
Call cartographer_check_depth. Fix every issue it reports. Call it again.
Repeat until passed: true. Do NOT report to the user until it passes.
Bad exploration (avoid)
- 50 entities, all flat, no sub-boundaries, no slices — a parts list
- Boundaries named "Service", "UI", "Plugin" — directory mirrors
- Descriptions like "Express middleware handler" — engineer jargon
- No behavior flows — structure without stories
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 · 68 lines · 53 tokens per session scan A 1e3dca2dcfbe
explore is a skill published in the GitHub repository miltonian/cartographer (1 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 617 once invoked, about $0.0003 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
ch015-va
Run CH015 vulnerability assessment workflows for source-code security architecture review, 8-dimension analysis, compliance checks, self-verification, evidence verification, and VA reporting.
ch015-verifier
Run CH015 adversarial verification workflows to independently validate security reports, recheck file-line evidence, find false positives, severity errors, missed findings, and dependencies.
ch015-feedback
Run CH015 security design review workflows for PRDs and specs to produce security opinions or review findings mapped to standards and regulatory requirements.
dekko-orient
Use dekko's tools instead of grep/Read whenever a repo has a .dekko/ directory — not just at session start. Trigger on any "find/locate/understand this symbol," "what does this file/dir contain," "what will this change break," or "read this file" impulse. dekko has already parsed and indexed the repo; grepping or…
dekko-daemon
Start dekko's background daemon before a session that will run many bare dekko CLI commands via Bash (not the MCP tools) against a large or medium repo. Trigger when you're about to run several dekko CLI invocations in a row on the same repo — a long refactor loop, a batch of query/search/outline calls, or a…
dekko-notes
Read and write dekko's symbol-anchored notes in any repo with a .dekko/ directory. Trigger every time you pull a symbol's context (querysymbol, getcontextpack, dekko query/context), right after a non-obvious change, and right after any rename/move/signature edit (to sweep orphaned notes). Notes are durable, committed…