ade-cli is a command-line tool for turning documents into structured, searchable content, including Markdown, document elements, and extracted fields with page-and-box evidence. It is used from a terminal to parse documents and retrieve schema-shaped data, while its bundled catalogue add-ons help coding agents operate the CLI.
Borrowing it
Nothing to install: this file belongs to landing-ai/ade-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/landing-ai/ade-cli/main/.claude/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/landing-ai/ade-cliWrote 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/landing-ai/ade-cli/verify)<a href="https://agentmods.dev/skills/landing-ai/ade-cli/verify"><img src="https://agentmods.dev/badge/skills/landing-ai/ade-cli/verify/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/landing-ai/ade-cli/verify"><img src="https://agentmods.dev/badge/skills/landing-ai/ade-cli/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00402 |
| Opus 5.5 | $0.00010 | $0.00161 |
| Sonnet 5.5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
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 2mo 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.
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.
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.
- 2mo ago First seen · 36 lines · 25 tokens per session scan A d6334fe1b80b
verify is a skill published in the GitHub repository landing-ai/ade-cli (2,425 stars, last pushed 5d ago), licensed Apache-2.0. It adds 25 tokens to every session and 402 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
BrowserBash Browser Automation
BrowserBash is a vendor-independent, natural-language browser automation CLI. Drive a real browser from plain-English objectives or committable Markdown tests, run on local Chrome, CDP/Playwright MCP, Browserbase, LambdaTest, or BrowserStack, and stream NDJSON results with CI exit codes — using free local Ollama…
test-app
Verify a running Mendix app in a browser: mxcli playwright check for a one-call text verdict per page (renders? error banner? console errors? rows?), playwright-cli scripts for interaction, OQL for data. Use when asked to check a page, see whether it renders, verify in the browser, test the app end to end, or confirm…
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; run or list flows…
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
agent-browser
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.