From Hermes's fork.49 re-dogfood (9/11 fixes confirmed PASS):
- tab list: a page can set its title to a multi-KB string (= a giant URL); cap
the title column like the URL so the row stays readable.
- skill: clarify that true multi-agent isolation needs the extension-connect path
(per-session tab groups) — raw `--cdp` shares the browser, so a sibling
session's `open` can navigate your tab. Use the extension for concurrent agents.
- skill: prefer `eval --json` for array/object results (plain render is
multi-line / pipe-hostile); note type/fill don't fire keydown (use `keyboard
type` when key events are required).
(Hermes's "find-text click bypasses humanize" was a false alarm — verified both
paths curve; the apparent 1-vs-12 was cursor continuity on the same target.)
Within a session, commands are pinned to the agent's opened tab (fork.47). But
two agents on the same (default) session share one daemon + active tab and
clobber each other. Document that each concurrent agent must use a unique
--session — which gives it its own isolated tab group on the shared real Chrome.
Local stealth verification with no external detector: reports mode (connect vs
launch), live fingerprint probes (navigator.webdriver / window.chrome / plugins /
UA-headless) as pass/fail, and an audit of the active overrides for the path
(incl. the iframe-proxy state from #4). `--json` for a stable shape agents can
gate a sensitive flow on. Distinct from `doctor` (install/env health).
The biggest manual-cost point in the dogfood reports: `select @ref` is a silent
no-op on non-native dropdowns, and click+wait+Enter on react-select/ARIA/portal
menus took ~20 turns of hand-written eval to get right.
New `pick <selector> --option "<text>"` does it atomically in one in-page async
routine: native <select> → set value + input/change; custom widget → focus +
open (pointer/mouse sequence), poll up to 2.5s for the option to render anywhere
(portals included), match by visible text, scroll it in, fire the full
pointer/mouse sequence. ERRORS loudly if the option never appears — no silent
success.
Verified headless: native <select> → "Gamma"; portal combobox → "欧洲"
(non-ASCII); missing option → explicit error. Documented in the skill.
- `eval --file <path>`: read JS from a file, sent verbatim — avoids shell-mangling
of non-ASCII identifiers/strings (Chinese), quotes, and large scripts (issue #3).
- `tab list`: truncate multi-KB URLs (JWT/OTP login links) middle-out with a char
count so the list stays readable (issue #3).
- skill: fix the snapshot example to match real output
(`- role "name" [ref=eN]`, not `@e1 [role]`); document that eval runs in the
page MAIN world with persistent state (top-level `const` collides — use IIFE /
window / unique names) and to prefer --file/--stdin/-b for non-ASCII or big JS.
- README + README.zh: new Anti-detection subsections — "Human-like input
(behavioural stealth)" (curved trajectories / jitter / cadence / eased
scroll-drag, adaptive per-page escalation, off|fast|human) with the
trajectory contrast table, and "Silent operation" (background tabs, no
foreground stealing, focus-emulated). Added AGENT_BROWSER_HUMANIZE to the
tuning-knobs table.
- skill core: agents told operation is silent by default and how/when to use
--humanize (leave on auto; force human for known behavioural targets).
Other users will hit the same "古董二进制" problem — an agent-browser-stealth
predating the relay-preference (fork.30) ignores the extension relay and pops
Chrome 136+'s "Allow remote debugging?" dialog. So when an agent hits that dialog,
the skill now says to:
1. check `agent-browser --version`; if < 0.27.0-fork.30, upgrade via install.sh
(the npm registry lags — Releases are source of truth), and remove any stale
npm/pnpm copy that shadows it (a tool bundling its own pinned copy needs that
upgraded too);
2. otherwise install the Store extension.
Stops the "keep retrying the raw port" loop.
Add a prominent callout near the top of the core skill asking agents that hit a
rough edge (confusing error, stale @ref, occluded click, flaky wait, missing
feature) to open a quick issue at
https://github.com/leeguooooo/agent-browser-stealth/issues with the command and
expected-vs-actual. Agent-filed friction is the cheapest, highest-signal way to
sharpen the tool (the Hermes dogfood runs already proved this).
The extension is now live on the Web Store
(knfcmbamhjmaonkfnjhldjedeobeafmk). Update the skill so agents:
- install from the Store (one-click, restart-stable, auto-updating) as the
primary path, with Load-unpacked demoted to a dev fallback (it can be disabled
on Chrome restart, silently dropping the relay).
- when they DO hit the "Allow remote debugging?" dialog (relay not live → raw-port
fallback), stop retrying and tell the user to install the Store extension once,
rather than repeatedly popping the consent dialog.
Release binaries / Build macOS ARM64 (push) Has been cancelled
Release binaries / Build macOS x64 (push) Has been cancelled
Release binaries / Build Linux ARM64 (push) Has been cancelled
Release binaries / Build Linux musl ARM64 (push) Has been cancelled
Release binaries / Build Linux musl x64 (push) Has been cancelled
Release binaries / Build Linux x64 (push) Has been cancelled
Release binaries / Build Windows x64 (push) Has been cancelled
Release binaries / Attach binaries to GitHub Release (push) Has been cancelled
- wait --url: the arg parser never read `--timeout`, so a non-matching pattern
waited the large default and wedged the daemon. Parse it. Also: matching was a
literal substring (`includes`) so globs never matched — convert `**`/`*`/`?`
globs to an anchored regex. And `poll_until_true` now bounds each probe with a
timeout and tolerates transient navigation errors, so a hung `Runtime.evaluate`
can never block past the deadline (un-wedges the daemon).
- find role <role> [--name]: the query was `[role="X"], X`, which matches a
literal <X> tag / explicit attribute but NOT implicit-role elements — so
`find role link` (<a href>) and `find role heading` (<h1>) never matched. Add a
proper ARIA-role → implicit-element map and broaden accessible-name matching
(aria-label/title/alt/value/text).
- click on a syntactically-invalid selector returned `✓ Done`: querySelector
throws, and Runtime.evaluate returned the thrown DOMException as an objectId
that was clicked as if it were the element. Check exception_details → error.
- output: a title-less page now prints `✓ <url>` instead of an empty title line.
- docs(skill): tab refs are `t2`, not `2` (SKILL.md, electron).
Verified live (isolated launch): wait --url glob matches instantly; non-matching
honors --timeout (2s) and leaves the daemon responsive; find role link/heading
match; invalid selector errors. Unit tests added for the glob + role map + parse.
Release binaries / Build macOS ARM64 (push) Has been cancelled
Release binaries / Build macOS x64 (push) Has been cancelled
Release binaries / Build Linux ARM64 (push) Has been cancelled
Release binaries / Build Linux musl ARM64 (push) Has been cancelled
Release binaries / Build Linux musl x64 (push) Has been cancelled
Release binaries / Build Linux x64 (push) Has been cancelled
Release binaries / Build Windows x64 (push) Has been cancelled
Release binaries / Attach binaries to GitHub Release (push) Has been cancelled
- extension: popup status page (paired/not-paired) so the listing has standalone
UI; renamed agent-browser-stealth + new icon (earlier in this line)
- store: upload zip strips manifest "key" (the Web Store forbids it); the unpacked
dir + .crx keep it. Submitted for review (item knfcmbamhjmaonkfnjhldjedeobeafmk).
- connect: native-messaging allowed_origins lists BOTH the local Load-unpacked id
(ciiljdlhd…) and the store-assigned id (knfc…), so either install path pairs.
- ci: launch-based jobs opt into AGENT_BROWSER_ALLOW_HEADLESS for display-less
runners (fixes Native E2E); + version-sync/dashboard/fmt/clippy/flaky-test repairs.
- docs: skill documents both install methods (Load unpacked now, Web Store later).
The fork's CI had never been green. Pre-existing failures:
- version-sync: check-version-sync.js read packages/dashboard/package.json,
which doesn't exist in this fork (workspace is just "."). Drop the dashboard
comparison; check package.json vs cli/Cargo.toml only.
- Dashboard job: `pnpm install --filter dashboard` for a non-existent package.
Remove the job.
- Format check: repo was never `cargo fmt`-clean. Ran cargo fmt (mechanical).
- Clippy -D warnings (newly enforced on Rust 1.94 stable): manual_contains in
commands.rs (.iter().any()->.contains()), question_mark in element.rs
(if-let-Err -> ?), result_large_err on the tungstenite handshake callback in
connect.rs (allow — the Result type is fixed by the accept_hdr_async contract).
- rust-cross: lightpanda::waits_for_ready_without_logs spawns a real process +
binds a socket with timing assumptions; flaky in CI. Marked #[ignore].
Also: skill docs note fork.30's relay-preferred auto-connect (plain
`agent-browser open` is dialog-free once the ab-connect extension is loaded) and
the extension's new "agent-browser-stealth" display name.
Update the served skill (skill-data/core, embedded into the binary) for tonight's
changes: --headed is the default and headless is FORBIDDEN (was wrongly 'default
is headless'); each --session on the extension-connect path gets its own colored
tab group with no cross-talk; anti-detection ranking real-Chrome(extension) >
headed-launch > headless(forbidden). Needs a rebuild so standalone installs'
embedded skill reflects it.
So an agent can operate the zero-confirmation real-Chrome feature itself:
- SKILL.md: tool matrix gains "the user's own already-open, logged-in window →
extension connect", plus a short section pointing at the flow.
- commands.md: the one-time "Load unpacked" is a privileged GUI step the CLI
can't do — call it out that the agent can perform it with a computer-use /
GUI-automation tool (cua-driver), with the live gotchas (synthetic-keystroke
tools like peekaboo don't reach Chrome; cua-driver does; the native file
dialog may need the user to pick the folder).
Completes the zero-confirmation real-Chrome feature.
- Drive the user's EXISTING logged-in tabs (not just newly-created ones):
extension attachTab now treats "already attached" (a lingering chrome.debugger
binding after a service-worker restart) as success and announces the tab
anyway, instead of skipping it. The nm-host also sends {method:"attachAll"}
when an agent-browser CDP client connects, so the daemon doesn't race an empty
target list.
- `agent-browser extension connect` auto-discovers the relay's CDP url
(~/.agent-browser/relay-cdp-url) and attaches — no copying a ws URL. Rewrites
into the normal `connect <url>` flow; `extension install/status/uninstall`
unchanged.
- Skill docs: a "drive your real, logged-in Chrome (extension)" section.
Verified end-to-end: `extension connect` listed the user's real tabs (Lark,
LINUX DO, Rakuten, Discord) and read a logged-in Lark doc's title — zero token,
zero confirmation. Full suite 768 passed.
Borrow web-access's site-experience persistence as an agent-workflow convention
(no CLI code): keep one markdown file per domain under
~/.agent-browser/site-patterns/<domain>.md. Read it before working a domain
(hints, not guarantees); update it after learning something durable — working
selectors, required hidden fields, anti-bot traps, login needs. Makes repeat
visits fast instead of re-solving the same page every run.
Borrow web-access's find-url: locate an internal system or a previously-saved
page that public search can't reach, without opening a browser.
- `agent-browser find-url <keywords> [--browser chrome|edge] [--profile X]
[--limit N] [--json]` — local command, no daemon. All keywords must match a
bookmark's name or url; results are most-recently-added first.
- Cross-platform Bookmarks JSON paths (macOS / Linux / Windows), zero new deps
(serde_json). Skips javascript:/data: bookmarklets.
- Skill docs: "pick the cheapest tool" matrix now points at find-url, plus a
commands.md section.
Bookmarks only for now — visited-history is a locked SQLite DB and would need a
SQLite dependency (deferred to avoid C-dep cross-compile risk in the release
pipeline).
Real dogfooding showed the skill pushed agents straight into the fragile
snapshot/@ref path. Reframe the core guidance toward how a developer actually
drives a real browser:
- "Pick the cheapest tool" matrix: WebSearch / WebFetch+curl for static, reach
for agent-browser only when you need a real logged-in / interactive / dynamic
browser. Plus: don't hand-build deep URLs — use links found by interacting.
- "Two ways to drive a page": structured (@ref/find) is convenient but lossy &
fragile; eval-first (`eval "<js>"`) is the real DOM — read hidden inputs,
Shadow DOM, form.elements/.validity, or el.click() directly. Drop to eval the
moment the structured path fights you, instead of retrying it.
- Escalation ladder rewritten (refs → find → CSS → eval) and a note to retry a
no-op click with AGENT_BROWSER_CLICK_MODE=dom.
Doc-only; closes the biggest part of the "abs feels worse than web-access" gap.
Real-world dogfooding surfaced clicks that resolve a valid @ref but still miss:
- Scroll the target into view before computing click coordinates
(scrollIntoViewIfNeeded). Without it, an element below the fold — or revealed
after a scroll/popup — yields off-viewport coordinates and the click lands on
whatever occupies that screen point.
- Fall back to a DOM-dispatched `.click()` when the coordinate path fails (a
persistent floating layer failing the occlusion guard, or coordinates that
won't resolve). The DOM dispatch targets the intended element directly instead
of a screen point, so an overlay or portal can't divert it.
- AGENT_BROWSER_CLICK_MODE: "" (default: scroll + coordinate + DOM fallback),
"coord" (strict coordinate, hard-fail on occlusion), "dom" (always
element.click() — best for autocomplete/menu <li> that close on input blur).
Fallback is limited to left single-clicks (DOM .click() can't express
right/middle/double). Non-left/multi and "coord" mode keep the original error.
Docs: README knob table + skill commands.md gain CLICK_MODE, a click-reliability
note, and a "debug forms/hidden inputs with eval" section (snapshot doesn't show
hidden inputs — the fast path to bugs like a hidden point_choice=none).
6 click/interaction e2e green; full suite 760 passed.
console/errors capture is off by default in this fork (Runtime.enable is a
detectable CDP signal). Update the agent-facing skill docs so agents don't
treat empty console output as a bug:
- commands.md: new "Stealth / anti-detection knobs" env-var block
(CAPTURE_CONSOLE, TIMEZONE, BLOCK_WEBRTC, HIDE_CANVAS, ADAPTIVE_REF) plus a
heads-up note; annotate the console/errors lines.
- dogfood/slack SKILL.md: note that console/errors need
AGENT_BROWSER_CAPTURE_CONSOLE=1.
Cherry-picks upstream agent-browser #1396. Adds a configurable
--hide-scrollbars flag (AGENT_BROWSER_HIDE_SCROLLBARS env, hideScrollbars
config key, default true) that appends Chrome's --hide-scrollbars launch arg
for headless (non-extension) launches so native scrollbars aren't painted into
screenshots. Plumbed through flags.rs, connection.rs, main.rs, native/actions.rs
and native/cdp/chrome.rs; help text in output.rs + skill-data.
Fork adaptation:
- the arg lands in the headless && !has_extensions block, separate from the
stealth base args — no interaction with anti-detection.
- dropped upstream docs/, agent-browser.schema.json and README hunks (removed
or rewritten in this fork).
Verified: cargo check --tests passes.
- Add fork binary names (agent-browser-stealth, abs) to allowed-tools
in all 6 SKILL.md files so installs into Claude Code / Cursor don't
prompt for permission on every command
- Document `npx skills add leeguooooo/agent-browser-stealth` in README
- Bump README upstream-base mention from v0.24.0 to v0.27.0
* feat(react): first-class React introspection, Web Vitals, and nextjs skill
Add React-general and web-universal features as first-class agent-browser verbs
(react tree/inspect/renders/suspense, vitals, pushstate). Genuinely Next.js-specific
workflows (PPR cookie protocol, /_next/mcp bridge, dev-server endpoints) ship as
a new `nextjs` skill that composes the primitives. No new runtime dependencies -
the React DevTools installHook.js is vendored (MIT) and include_str!'d into the
binary.
New commands:
react tree Full React component tree (depth id parent name)
react inspect <fiberId> Props, hooks, state, source for one fiber
react renders start|stop Fiber profiler with Insts/Mounts/Re-renders/Self/DOM
+ prev->next change details
react suspense Suspense boundaries + classifier (client-hook,
request-api, server-fetch, cache, stream, framework)
+ root-cause grouping + recommendations
vitals [url] LCP/CLS/TTFB/FCP/INP + React hydration phases
pushstate <url> Generic SPA client-side navigation
removeinitscript <id> Remove a script registered via addinitscript
New launch flags:
--init-script <path> Register init scripts before first navigation
(repeatable; env AGENT_BROWSER_INIT_SCRIPTS)
--enable <feature> Built-in init scripts; currently react-devtools
(repeatable; env AGENT_BROWSER_ENABLE)
Other primitives:
network route ... --resource-type <csv> Filter by CDP resource type
cookies set --curl <file> Auto-detects JSON/cURL/Cookie-header
* fixes
* fixes
* fixes
Before this change, the main skill served by the CLI (`agent-browser
skills get agent-browser`) was a ~40-line discovery stub whose content
was essentially "run `agent-browser skills get <name>` before doing
anything." Agents already inside the CLI got no signal from it — the
content they needed to actually use the tool lived only in the `--full`
references.
Split the two jobs apart:
- **`skill-data/core/`** (new) — the runtime usage guide. 420-line
`SKILL.md` covering the snapshot-and-ref loop, common workflows
(login, extract, screenshot, multi-tab, sessions, iframes, dialogs),
waiting strategies, element selection strategies, troubleshooting,
and when to load a specialized skill. Supplementary `references/` and
`templates/` (moved from `skills/agent-browser/`) provide the full
command reference under `--full`.
- **`skills/agent-browser/SKILL.md`** — still the discovery stub that
`npx skills add` installs, now marked `hidden: true` so it stays out
of `skills list` inside the CLI. Body is a clean pointer to
`agent-browser skills get core` and the specialized skills.
The `hidden: true` frontmatter flag is a new, general mechanism: skills
marked hidden are omitted from `skills list` and `skills get --all` but
can still be fetched by explicit name. This keeps the stub reachable
for anyone who installed via `npx skills add` without polluting the
CLI-side skill listing.
## Behavior
```
$ agent-browser skills list
agentcore Run agent-browser on AWS Bedrock AgentCore cloud browsers...
core Core agent-browser usage guide. Read this before running...
dogfood Systematically explore and test a web application...
electron Automate Electron desktop apps (VS Code, Slack, Discord...)
slack Interact with Slack workspaces using browser automation...
vercel-sandbox Run agent-browser + Chrome inside Vercel Sandbox microVMs...
$ agent-browser skills get core # the actual usage guide
# ~420 lines of workflows, patterns, troubleshooting
$ agent-browser skills get agent-browser # still works if called explicitly
# the thin stub, now pointing at `core`
```
External `npx skills add vercel-labs/agent-browser` behavior is
unchanged: it finds and installs the thin `agent-browser` stub, which
tells the agent to run `agent-browser skills get core` for real
content. Version drift protection is preserved — the stub is the only
thing that gets copied; the real content is always runtime-fetched.
## Updated
- `cli/src/skills.rs` — `SkillInfo.hidden: bool`, parsed from
frontmatter; `run_list` and `run_get --all` filter it. 3 new unit
tests for the frontmatter parser.
- `cli/src/output.rs` — top-level `--help` and `skills` subcommand help
reference `skills get core` / `skills get core --full`.
- `AGENTS.md` — "update these files for user-facing features" now
points at `skill-data/core/` instead of the stub, with a note that
the stub is not the right place for feature content.
- `README.md`, `docs/src/app/skills/page.mdx` — describe the new
split and `skills get core --full` as the recommended entry point.
- `evals/cases/{command-usage,skill-selection}.ts` — expect
`skills get core` in agent output instead of `skills get
agent-browser`. Eval lib still reads `skills/agent-browser/SKILL.md`
(simulating what an agent sees after `npx skills add`).
All 11 skills unit tests pass. `cargo clippy -- -D warnings` and
`cargo fmt --check` clean. Verified end-to-end: `skills list` shows
`core` + specialized (no stub), `skills get core` returns the new
content, `skills get agent-browser` still returns the stub on explicit
request.
The skills CLI metadata.internal flag was never implemented (PRs #587
and #652 were both closed). All 6 skills were showing in the installer.
Move the 5 specialized skills (dogfood, electron, slack, vercel-sandbox,
agentcore) from skills/ to skill-data/, which the skills CLI does not
search. The bootstrap skill stays in skills/ for discovery. The Rust CLI
searches both directories so agent-browser skills list/get still serves
all 6.
leeguooooo