verify

A verification guide for ade, a tool that extracts information from documents. It explains how to prepare test data offline, run the command-line tool, and inspect the generated document view in a browser.

In plain words
What is it for?
Use it to seed a local document store, run ade, open its generated view, and verify extracted elements and deep links.
Why use it?
It lets you test the complete workflow without calling the document service, while checking that stored data and visual selections match.

Skill for Claude CodeCodex

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/landing-ai/ade-cli/verify
Any agent
npx skills add landing-ai/ade-cli --skill verify
Clone the repo
git clone --depth 1 https://github.com/landing-ai/ade-cli

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 402 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 $0.00025 $0.00402
Opus 5 $0.00013 $0.00201
Sonnet 5 $0.00005 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured 3d ago against content hash d6334fe1b80b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/skills/verify/SKILL.md · 36 lines

What it actually says

Verifying ade

Build/run: uv sync, then uv run ade …. Tests are offline (fake transport); verification means driving the real CLI against a real store.

Seeding a parsed doc without the network

parse needs the API, so seed the store directly — write what parse would have written (see parse.py::write_artifacts for the exact set): parse.json (raw ParseResponse), parse.md, elements.json ({"job_id", "elements": elements.project(response)}), meta.json (state: "parsed", job_id matching parse.json's metadata.job_id — the generation gate in refs.live_parse rejects mismatches).

A ready-made seeder that also draws a matching invoice PNG (so boxes visibly align) was used for the view verification — pattern: build markdown piecewise so every element's range is exact, reuse tests/parse_fixtures.py shapes.

Point the CLI at the seeded store with ADE_HOME=<dir>.

Driving view.html

The in-app browser refuses file:// — serve the doc dir instead: python3 -m http.server 8742 --bind 127.0.0.1 in $ADE_HOME/docs/<doc-id>/, then browse http://127.0.0.1:8742/view.html. Deep links: append #element=<id>. Selection state is inspectable via JS: document.querySelectorAll('.sel') (both panes share data-id). Rebuilds are fingerprint-gated — --json reports built: true|false; touching the source or changing --dpi forces a rebuild.

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. 3d ago First seen · 36 lines · 25 tokens per session scan A d6334fe1b80b

Subscribe to this mod's changes

verify is a skill published in the GitHub repository landing-ai/ade-cli (2,410 stars, last pushed 14d ago), licensed Apache-2.0. It adds 25 tokens to every session and 402 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

e2e-deployment-skill

Use this deployment skill to verify shared skills load during Playwright startup.

danny-avila/LibreChat · 22 tokens

launch

Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test…

microsoft/vscode · 96 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

anthropics/skills · 35 tokens

actionbook-web-test

Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…

actionbook/actionbook · 71 tokens

web-preview

Flutter Web版をビルド → サーバー起動 → Playwright でアクセス確認 → URLをユーザーに案内する。.

K9i-0/ccpocket · 32 tokens