Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add miltonian/cartographer/plugin install 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/verify)<a href="https://agentmods.dev/skills/miltonian/cartographer/verify"><img src="https://agentmods.dev/badge/skills/miltonian/cartographer/verify.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 5.1 | $0.00081 | $0.01341 |
| Opus 5 | $0.00041 | $0.00671 |
| Sonnet 5 | $0.00016 | $0.00268 |
| Haiku 4.5 | $0.00008 | $0.00134 |
Grade A, and why
verify 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Loop
A closed feedback loop you can run entirely yourself. It boots your current source (not the marketplace clone), seeds a known model, and lets you observe and assert every layer — including the rendered pixels.
The whole stack runs in one process (src/index.ts serves MCP over stdio and
the HTTP API + UI), and the UI is origin-relative, so a single dedicated port
gives you a consistent, isolated system to verify.
When to use
After changing anything in src/ (store, API routes, projection) or ui/.
Run this before considering the change done.
The loop in one command
node scripts/verify/harness.mjs run
This: stops any prior harness server → rebuilds the UI iff ui/ is newer
than dist/ui → boots source on port 3947 against the golden fixture →
runs the API data-layer assertions → runs the MCP write-path smoke →
runs the project-root resolution regression → prints PASS/FAIL and leaves
the server up for the visual checks below.
The project-root regression (assert-project-root.mjs) guards a fixed bug: the
server must map CLAUDE_PROJECT_DIR (the user's project), not its own cwd
(which start.sh clobbers on marketplace installs). It boots an isolated server
on a separate port and asserts projectRoot resolves correctly.
When done: node scripts/verify/harness.mjs down.
Other commands: up (boot only), down (stop + clean), status (is it up?).
Then verify the pixels (Playwright MCP)
The scripted run proves the data layer. Now confirm the rendered map. The
server is at the URL printed by run (read scripts/verify/out/endpoint-port).
⚠️ Do the visual checks after the scripted asserts, in this order. Some interactions (semantic zoom) persist server state (a boundary perspective is written to the store), so the model drifts. If you re-run
assert-apiafter interacting, firstharness.mjs upto re-seed a fresh fixture.
- Overview renders.
browser_navigateto the URL. Thenbrowser_evaluate: expect.react-flowmounted,.react-flow__nodecount 8,.react-flow__edgecount 4, and the empty-state text absent.browser_take_screenshot→scripts/verify/out/01-map-overview.png. - Semantic zoom. Dispatch a bubbling
clickon.react-flow__node[data-id="boundary:Authentication"](the boundary center is covered by children, so a normal center-click won't reach it; a dispatched bubbling click triggers React's delegated handler). Expect the URL to gain?perspective=perspective%3AAuthentication, a breadcrumbOverview › Authentication, and the node set to become the 3 auth children + Charge card (contextual, because Verify credentials invokes it cross-boundary). - Flow highlight. Navigate back to
/. Click the "User login" button in the FLOWS panel (it is a toggle — click once). Expect its label to turn accent (rgb(129, 140, 248)), the 3 flow nodes to show numbered step badges (1, 2, 3), and the 3 non-flow nodes to dim to opacity 0.25. - Console clean.
browser_console_messagesat levelerror,all: true→ expect 0.
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.
- 5d ago First seen · 109 lines · 81 tokens per session scan A 88298f871330
verify is a skill published in the GitHub repository miltonian/cartographer (1 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 1,341 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.
Other skills, from other repositories
unit-test
기능 단위 테스트 오케스트레이터. Git Diff/사용자 지정 범위에서 테스트 대상을 결정하고, 사용자 시나리오 스토리보드 → 테스트케이스 생성 → Playwright MCP 실행 → 결과 보고. '/unit-test', '단위테스트', '테스트해줘', '기능 테스트' 등 언급 시 호출. 시나리오 단위 회귀 검증(PASS/FAIL/WARN)에 사용하며, 버그 원인 특정·로그 삽입 디버깅이 필요하면 debugger 계열 스킬을 쓴다.
test-site
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
recipe-add-integration-tests
Add integration/E2E tests to existing codebase using Design Docs.
feature-verify
Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use feature-dev), code review (use codex-review-fast), writing tests (use codex-test-gen), security audit (use…
test-implement
Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness. Use when creating or completing frontend tests and generated test skeletons.
verify
Verification loop — lint -> typecheck -> unit -> integration -> e2e.