opencli-usage

OpenCLI turns websites into a uniform opencli <site> <command> surface that agents can drive without screen-scraping. This skill is the orientation layer — once you know what you want to do, load one of the specialized skills below.

Main capabilities

• Adapter commands — opencli <site> <command> [...]. Built-in adapters live in clis/, user adapters in ~/.opencli/clis/. Each is backed by a strategy (PUBLIC | COOKIE | INTERCEPT | UI | LOCAL) that tells you whether a Chrome session is needed.
• Browser driving — opencli browser * subcommands (open, state, click, type, select, find, extract, network, …) for ad-hoc interaction and scraping when no adapter covers the task. See opencli-browser.
• Current-tab binding — opencli browser <session> bind attaches the Chrome tab the user already opened/logged into to that browser session. Follow-up commands use opencli browser <session> .... See opencli-browser before using it; bound sessions still block tab mutation.

Install

# npm global
npm install -g @jackwener/opencli          # binary: opencli, requires Node >= 20.18.1
opencli doctor                              # run before browser-dependent work (see below)

# From source
git clone git@github.com:jackwener/OpenCLI.git
cd OpenCLI && npm install
npx tsx src/main.ts <command>               # same surface, no global install

opencli doctor prints a structured DoctorReport — daemon status, extension connection, version checks, and a live browser connectivity probe. Scope is narrow: it diagnoses the browser bridge (daemon + extension + Chrome wiring). PUBLIC / LOCAL adapters, opencli list, validate, verify, and plugin commands don't need it to be green — only COOKIE / INTERCEPT / UI adapters and the opencli browser * subcommands do. Flag: -v (verbose).

Prerequisites by command type

Discover what's installed — don't read this file, run a command

opencli list                    # table, grouped by site
opencli list -f json            # machine-readable; pipe to jq or your agent
opencli list | grep -i twitter  # find commands for a specific site
opencli <site> --help           # see that site's commands + flags
opencli <site> <command> --help # see positional args and command-specific flags

Do not hard-code adapter lists — there are 100+ sites and the count moves every week. opencli list -f json is the source of truth; it emits one entry per command with {site, name, aliases, description, strategy, browser, args, columns, ...}. For an agent, that is always better than grepping a doc.

Before falling back to raw opencli browser commands on high-change authenticated sites, check whether a site adapter already exposes the workflow. For example, ChatGPT web has higher-level commands for conversation reads and Deep Research result extraction; discover the current surface with opencli chatgpt --help or opencli list -f json.

Universal flags (work on every adapter command)

Command-specific flags (--limit, --tab, --filter, …) are not universal — consult <site> <command> --help.

Output formats

• json — pretty-printed, 2-space indent. Default choice for agents.
• plain — prints a single primary field for chat-style commands (response/content/text/value). Useful for piping to another tool.
• yaml — fallback when output is not a TTY and -f is not explicit.
• table — color-coded, site-grouped; meant for humans.
• md, csv — straightforward tabular dumps.

A few commands override the default via cmd.defaultFormat (e.g. chat commands default to plain), so don't assume without reading --help.

Environment variables

Self-repair

When an adapter command fails because the site changed (selectors drifted, API rotated, response schema shifted), re-run with --trace retain-on-failure. The error envelope includes a trace block pointing at summary.md; patch only the adapterSourcePath from that summary and retry. Max 3 repair rounds. The full flow is in opencli-autofix.

Writing your own adapter

Two-path storage:

• Private: ~/.opencli/clis/<site>/<command>.js — no build step, hot-available, not visible in the public package.
• Public / PR: clis/<site>/<command>.js — for upstream contribution; requires build.

Scaffolding & verification:

opencli browser init <site>/<command>   # generates a skeleton
opencli validate [target]               # semantic checks on the loaded registry (description, domain, pipeline step names, func|pipeline|_lazy presence, arg duplicates) — no network, no browser
opencli verify [target] [--smoke]       # run the command with synthetic args
opencli browser verify <site>/<command> # end-to-end smoke inside the bridge

Adapters import only @jackwener/opencli/registry and @jackwener/opencli/errors. columns must align 1:1 (in name and order) with keys of the object returned by func. For the full workflow see opencli-adapter-author.

Plugins

Plugins are third-party extensions pulled from git, separate from the main adapter registry:

opencli plugin install github:user/repo    # install
opencli plugin list [-f json]              # see installed
opencli plugin update [name] | --all       # keep current
opencli plugin uninstall <name>
opencli plugin create <name>               # scaffold a new plugin

Shell completion

opencli completion bash   # also: zsh, fish
# -> script on stdout; source or save per your shell's convention

Where to go next

Commands that used to exist

The following were removed in the PR #1094 consolidation — don't try to invoke them:

• opencli explore <url> — superseded by opencli browser network + opencli browser find for live API discovery, and by the opencli-adapter-author workflow for capture.
• opencli record <url> — removed; manual capture now lives in opencli browser network --detail.
• opencli web read / opencli desktop * as top-level groups — folded into their respective adapters (opencli web read still exists as the web adapter's read command, but there is no standalone web / desktop top-level group command).

Don't

• Don't paste this skill's command list into your plan; it will rot. Call opencli list -f json at the start of a task instead.
• Don't assume every adapter needs a browser — strategy PUBLIC and LOCAL don't. Check the strategy field.
• Don't silently fall back from a failing adapter to a hand-rolled fetch — --trace retain-on-failure gives you the browser evidence and adapter source path. Do that first.