Browser

opencli-browser-sitemap

Try it

Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live browser state.

What it does

Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live browser state.

The skill document

opencli-browser-sitemap

Use this skill when opencli browser open or opencli browser analyze reports sitemap.available: true, or when the user asks you to use a site's sitemap.

The sitemap is prior knowledge, not ground truth. It should reduce blind clicking, but it must never override the live browser state.


Consumption Loop

  1. Run or reuse opencli browser state to know the current page.
  2. Read only the smallest relevant sitemap files:
    • SITE.md for site-level orientation.
    • One matching pages/.md for current state.
    • One matching workflows/.md for the user goal.
    • pitfalls.md only when blocked or warned by the workflow.
  3. Prefer the workflow's Best path. If it names an adapter such as opencli twitter post, use that before raw browser actions.
  4. If the adapter is unavailable or fails, use the Fallback path browser workflow.
  5. After each navigation or state-changing action, refresh state and compare the workflow's state_signature.
  6. If reality disagrees, trust reality, continue probing, and write a local stale note or draft patch.
  7. If an action recovery includes adapter_health_update: -> suspect|broken, update the local overlay workflow that references that adapter so future agents go straight to the fallback path.

Lookup Order

Read local overlay first, then global seed:

~/.opencli/sites//sitemap/    # local overlay
sitemaps//                    # repo seed (top-level)

Local files override global files with the same stable id.

Do not load an entire large sitemap into context. If the directory is large, list filenames first and then read only the page/workflow you need.


Trust Reality Rule

If sitemap says a button, URL, route, or API should exist but the browser does not show it:

  • Re-run state or find with semantic anchors.
  • Check whether login, locale, viewport, A/B test, or route state differs.
  • Follow the real page if a safe path is visible.
  • Mark the sitemap item stale in local overlay.

Never keep clicking because "the sitemap says it should work."


Stale / Draft Notes

When you discover drift, write a small local note under the relevant page/workflow file or a draft file in the local overlay:

Stale note:
- observed_at: YYYY-MM-DD
- current_url:
- expected:
- actual:
- next_probe:

Do not edit global seed files unless the task is explicitly a sitemap-authoring or repo PR task.

Adapter Health Write-Back

When an adapter fails and the sitemap action or workflow tells you to update adapter health:

  1. Find the local workflow file under ~/.opencli/sites//sitemap/workflows/ whose Best path references the adapter command.
  2. If no local workflow exists, copy the matching global workflow into the local overlay first; never edit the global seed directly during browser task execution.
  3. Set adapter_health: suspect or broken as directed.
  4. Add a short stale note with observed error, current URL, and timestamp.
  5. Continue with the browser fallback path.

This write-back is the memory loop: the current agent falls back once, and the next agent does not waste a turn retrying a known-suspect adapter.


Output Discipline

When reporting back, include:

  • Path chosen: adapter best path or browser fallback.
  • Checkpoint reached: current URL/state signature.
  • Sitemap health: used as-is, stale marked, or missing workflow.

Keep the report task-focused. Do not summarize the whole sitemap.

Related skills

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking...

by Nicolas Kleiber15 installs1 stars

Agent Browser is a powerful headless browser automation CLI designed for AI agents. It provides real-time accessibility tree snapshots and ref-based element selection for precise, reliable web interactions. Optimized for autonomous agents, it enables seamless navigation, form filling, and data extra

Use when AI agents need to read, inspect, operate, navigate, debug, or verify browser state through the omnibot CLI and connected Chromium extension.

1 stars

Lets your AI agent drive a real Chrome session (yours or a marketplace participant's) for tasks where headless or scripted requests are not enough — your own...

2 installs