browser SKILL.md skillA

browser from agentproto/ts is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add agentproto/ts/browser@git:20260717.c271e80

Pins git:20260717.c271e80 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
agentproto/ts
Path
packages/skill-pack-bureau/src/skills/browser/SKILL.md
Versions recorded
1
Latest version
git:20260717.c271e80, committed Jul 17, 2026
Size
5,867 bytes
Repository stars
10
License
Apache-2.0

Drive the user's REAL authenticated browser (their logins/cookies) via the local-browser chain — guilde → tunnel → daemon → chrome-devtools-mcp → cloned Chrome. The foundation skill for any "do X in a browser as me" task: navigate, capture (element screenshots + selective content/ld+json/readability), inspect network, manage tabs/cookies/consent, and — for data — talk to a site's OWN internal API instead of its fragile DOM. Site-specific recipes are separate skills…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Browser — the authenticated-browser capability

**The browser is an authenticated transport to the user's real sessions.** Read
data from each site's own internal API (ground truth) and use the DOM only for
visuals + the few write buttons. Proven: on a hardened SPA the DOM yields ~0
useful data while an in-page API fetch returns the full structured truth.

## Where each concern lives (three homes, one boundary)

- **Capability = code.** The social capture/search recipes are implemented in
  `@agstudio/browser-social` (the `SOCIAL_PLATFORMS` adapters +
  `createLinkedInVoyager`). Drive the adapter; don't re-derive a recipe by hand.
- **Operator "how/when" = corpus playbook.** The durable judgement a _runtime_
  agent carries (recon SOP, persona = four signals, person-id scoring,
  when-to-escalate-stealth, rate-limit + write-gating discipline) is the
  `social-recon` corpus playbook overlay, injected into the operator's prompt
  (`projects/guilde/packages/builtins/src/knowledge/social-recon.ts`; read path
  in `apps/api/src/mastra/guilde-playbook-processors.ts`). A runtime operator
  cannot read these dev skills — the playbook is its home for that knowledge.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add agentproto/ts/browser@sha256:7448317e5556350a

The line at the top of this page pins the label git:20260717.c271e80, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lyuxysnawi2i3c5k.svg)](https://markdownregistry.com/a/art_lyuxysnawi2i3c5k)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 17, 2026.

versioncommittedcommitsizeaudit
git:20260717.c271e80 latest2026-07-17 c271e80 5,867 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5867 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

agentproto/ts · 10 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lyuxysnawi2i3c5k
GET https://markdownregistry.com/api/v1/resolve?ref=agentproto/ts/browser
GET https://markdownregistry.com/api/v1/blob/7448317e5556350a7e393da5201973bf78514570aad2f4ff0882ff4439e59960

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from agentproto/ts

DESIGN.md@.plans/supervision-events DESIGN.md file
agentproto/ts · .plans/supervision-events/DESIGN.md
git:20261005.5a33dd6 · audit A · 10 stars
AGENTS.md AGENTS.md file
agentproto/ts · AGENTS.md
git:20261022.d1e8263 · audit A · 10 stars
CLAUDE.md CLAUDE.md file
agentproto/ts · CLAUDE.md
git:20260715.260841f · audit B · 10 stars
session-steward SKILL.md skill
agentproto/ts · packages/apps/session-steward/skill/SKILL.md · Wrap up idle agentproto agent sessions — classify them, close the safe ones, judge the ambiguous ones. Use when the…
git:20261010.f3665ea · audit A · 10 stars
install-agentproto-app SKILL.md skill
agentproto/ts · packages/create-agentproto-app/templates/book/_claude/skills/install-agentproto-app/SKILL.md · Register this directory's agentproto app bundle with the local agentproto CLI so the daemon can find and run it…
git:20260902.4d01e5c · audit A · 10 stars
agentproto-apps SKILL.md skill
agentproto/ts · packages/skill-pack-agentproto/src/skills/agentproto-apps/SKILL.md · Author, develop, and package an agentproto APP (AIP-53) — the real CLI path: `agentproto app init` → edit…
git:20261019.d7f5063 · audit A · 10 stars
agentproto-llm-endpoint SKILL.md skill
agentproto/ts · packages/skill-pack-agentproto/src/skills/agentproto-llm-endpoint/SKILL.md
git:20261024.97a0074 · audit B · 10 stars
agentproto SKILL.md skill
agentproto/ts · packages/skill-pack-agentproto/src/skills/agentproto/SKILL.md · Drive and supervise agentproto, the AIP-45 host daemon that runs agent CLIs. Use when spawning sessions (claude-code…
git:20261027.6a4d5c2 · audit B · 10 stars
ap-adapters SKILL.md skill
agentproto/ts · packages/skill-pack-agentproto/src/skills/ap-adapters/SKILL.md · Install and inspect agent CLI adapters (harnesses) on the agentproto daemon — adapter_list, adapter_install…
git:20260901.0259d5f · audit B · 10 stars
ap-apps SKILL.md skill
agentproto/ts · packages/skill-pack-agentproto/src/skills/ap-apps/SKILL.md · Install and run agentproto APPs (AIP-53 bundles of agents and workflows) — app_install, app_apply/unapply to scopes…
git:20261024.97a0074 · audit A · 10 stars
ap-cron SKILL.md skill
agentproto/ts · packages/skill-pack-agentproto/src/skills/ap-cron/SKILL.md · Schedule recurring or one-shot jobs on the agentproto daemon — cron_create with command, agent, or prompt-session…
git:20261027.d9a8be3 · audit A · 10 stars
ap-import-mcp SKILL.md skill
agentproto/ts · packages/skill-pack-agentproto/src/skills/ap-import-mcp/SKILL.md · Discover, import, and call external MCP servers from the agentproto daemon — mcp_discovered_list to find servers in…
git:20260901.0259d5f · audit A · 10 stars

Every file in agentproto/ts

Other files named browser

browser SKILL.md skill
code-yeongyu/oh-my-openagent · packages/shared-skills/skills/browser/SKILL.md · Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into…
git:20261106.e313b72 · audit A · 70,763 stars
browser SKILL.md skill
vibiumdev/vibium · skills/browser/SKILL.md · Automate browsers with the Vibium CLI. Use to navigate websites, inspect pages, fill forms, extract page data, debug UI…
git:20261104.bf5ce53 · audit A · 2,947 stars
browser SKILL.md skill
mindsdb/anton · anton/core/memory/builtin_skills/browser/SKILL.md · 'Recall BEFORE the first browser tool call in a task, and whenever a
git:20261109.b85528d · audit A · 757 stars
browser SKILL.md skill
agent-sh/agnix · tests/fixtures/mcp-clients/.agents/skills/browser/SKILL.md · Browses web pages. Use when the user asks to read a web page.
git:20261017.3b8047d · audit B · 472 stars
browser SKILL.md skill
spencermarx/open-code-review · .claude/skills/browser/SKILL.md · Web browser automation with AI-optimized snapshots for claude-flow agents
v1.0.0 · audit A · 382 stars
browser SKILL.md skill
betterwright/betterwright · SKILL.md · Drive a persistent, policy-guarded real web browser via the betterwright CLI. Use for any task that needs the live web…
git:20261104.b8831e7 · audit A · 349 stars
browser SKILL.md skill
blackbelttechnology/pi-agent-dashboard · packages/extension/.pi/skills/browser/SKILL.md · Browser automation via the `agent-browser` CLI. Use when the user needs to drive websites or Electron apps —…
v1.2 · audit A · 341 stars
browser SKILL.md skill
gtapps/hermitd · plugins/hermitd/skills/browser/SKILL.md · Drives the agent's own browser, or the operator's Chrome for their accounts. Use when WebFetch or WebSearch fails…
git:20261106.f32732e · audit A · 84 stars

Browse by kind, by grade A, or by owner.