pi-chrome 0.15.0: README rewrite — top-3 recipes, sharper comparison table, section reorder

4 files changed, 137 insertions, 106 deletions

diff --git a/CHANGELOG.md b/CHANGELOG.md
index d384e79..70f064f 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,12 @@
 
 All notable user-facing changes to `pi-chrome`.
 
+## 0.15.0 — 2026-05-13
+
+- **README rewrite — top-3 recipes as terminal mockups.** PR triage, Linear standup, and Bug-repro-with-evidence each get a copy-pasteable prompt → tool trace → result block modeled on the hero example. The other six recipes (form auto-fill, admin cross-check, visual diff, auth-only data pull, network forensics, file upload) collapsed into a `<details>` block so the section sells before it catalogs.
+- **Comparison table rewritten.** Dropped the all-✅ "Works on strict-CSP pages" row (zero signal). New table leads with "Time from `pi install` → first useful action on your real account" (~60s vs. hours) and "Survives MFA / SSO without code" (✅ already logged in). Multi-session row reframed as the bolded "Multiple agents drive the same Chrome at once". Footnote ² rewritten to highlight mode-aware scoring + open invitation for competing tools to PR their scores.
+- **Section reorder: sells before catalogs.** New flow: hero → 60-second install → 30-second try-this → killer recipes → comparison → honest results → tool catalog → click/watch modes (with Diagnostics folded in) → architecture → benchmark suite → security model & why unpacked (combined) → composes-with → roadmap → contributing → license. Hero blockquote now precedes shields badges so pi.dev no longer scrapes a broken-image badge as the description. Package `description` shortened to 255 chars so pi.dev hero stops truncating mid-word. `author` set to `"tianrendong (Earendil Inc.)"`.
+
 ## 0.14.9
 
 - Primer (agent system prompt) now teaches the **trusted-mode escape hatch** explicitly. Previously the bridge would hit a CSP-locked page (github.com, banks, many SaaS apps), `chrome_evaluate`/`chrome_snapshot` would throw `EvalError: 'unsafe-eval' is not an allowed source of script`, and the agent would conclude *"bridge can't drive this page"* and ask the user for a fallback. New primer makes three things self-discoverable: (1) `trusted: true` on click/type/key/fill/hover/drag/scroll dispatches through chrome.debugger / CDP and bypasses page CSP entirely, (2) the recipe for strict-CSP pages is `chrome_screenshot` + trusted input at viewport coordinates, (3) when synthetic input produces no `pageMutated` or you see a CSP/eval error, **escalate to `trusted: true` yourself instead of asking the user**. Also corrects the old claim that `chrome_evaluate` works without `'unsafe-eval'` (it does not — Function constructor is gated by `script-src`).
diff --git a/README.md b/README.md
index b01487b..156d35d 100644
--- a/README.md
+++ b/README.md
@@ -1,12 +1,10 @@
 # pi-chrome
 
-[![npm version](https://img.shields.io/npm/v/pi-chrome.svg)](https://www.npmjs.com/package/pi-chrome)
-[![npm downloads](https://img.shields.io/npm/dm/pi-chrome.svg)](https://www.npmjs.com/package/pi-chrome)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)
-
 > **The fastest way to give a [Pi](https://pi.dev) agent your real Chrome.**
 > No CDP. No throwaway profile. No re-login. Watch it work — or run silent.
 
+**MIT · 0 runtime deps · loopback-only bridge (`127.0.0.1:17318`) · inspect [`extensions/chrome-profile-bridge/browser-extension/`](./extensions/chrome-profile-bridge/browser-extension) before loading.** Verify connectivity in one command: `/chrome doctor`.
+
 ```text
 You:    "Find my open GitHub PR tab, summarize review state, and screenshot the failing CI."
 Agent:  chrome_tab(list) → chrome_snapshot(uid:…) → chrome_screenshot(...)
@@ -14,46 +12,11 @@ Agent:  chrome_tab(list) → chrome_snapshot(uid:…) → chrome_screenshot(...)
 You:    [keeps coding — agent never asked you to log in]
 ```
 
-`pi-chrome` ships **20+ browser tools** for Pi agents, backed by a small MIT-licensed Chrome extension that runs inside the Chrome profile **you already use** — including every site you're already signed into.
-
----
-
-## Why pi-chrome vs. everything else
-
-> Short version: **pi-chrome is primitives — "Playwright for the Chrome you're already signed into."** Not an agent loop. Plug it under any agent framework (Browser Use, Stagehand, LangGraph) or call its tools directly from a Pi agent. See [docs/COMPARISON.md](./docs/COMPARISON.md) for the full three-axis landscape (drivers, agents, cloud providers).
-
-|                                | **pi-chrome**                     | Playwright / Puppeteer        | CDP-based agents              | Selenium / WebDriver          |
-| ------------------------------ | --------------------------------- | ----------------------------- | ----------------------------- | ----------------------------- |
-| Uses your real signed-in Chrome | ✅ yes (extension in your profile) | ❌ throwaway profile            | ⚠️ requires `--remote-debug` | ❌ throwaway profile            |
-| Re-login required               | **Never**                         | Every run                     | Sometimes                     | Every run                     |
-| Watch agent work, live          | ✅ default; toggle quiet          | ❌ headless or new window      | ⚠️ debugger banner always     | ❌ new window                  |
-| Works on strict-CSP pages       | ✅ `new Function` MAIN-world      | ✅                             | ✅                             | ✅                             |
-| Real browser-trusted clicks     | ✅ opt-in (`chrome clicks on`)    | ✅                             | ✅                             | ✅                             |
-| Multi-session safe              | ✅ shared local bridge            | ❌ port collisions             | ❌                             | ❌                             |
-| Network/console capture         | ✅ built-in                       | ✅                             | ✅                             | ⚠️ via extensions             |
-| Honest result envelopes¹       | ✅                                 | ⚠️                            | ❌                             | ❌                             |
-| Built-in benchmark suite²      | ✅ 38 primitives + 4 long-horizon  | n/a                           | n/a                           | n/a                           |
-
-¹ Every action returns `pageMutated`, `defaultPrevented`, `elementVisible`, `occludedBy`, and `valueMatches` so the agent knows when a click didn't take effect — instead of looping blindly.
-² See [`test-suite/`](./test-suite) — 38 primitive challenges plus 4 hermetic BrowserGym-style tasks. Scoring is expected-outcome-by-mode (`synthetic` / `trusted` / `manual`), not raw PASS count. Pages grade any browser-control tool on trusted clicks, pointer humanization, keyboard fidelity, drag/drop, clipboard, Shadow DOM, iframes, file uploads, network capture, and fingerprint leaks.
-
----
-
-## What an agent gets
-
-**20 tools**, grouped by job. Every one runs against your already-open tabs.
-
-| Category        | Tools                                                                                          |
-| --------------- | ---------------------------------------------------------------------------------------------- |
-| **Tabs**        | `chrome_tab` (list/new/activate/close/version), `chrome_launch`                                |
-| **Inspect**     | `chrome_snapshot` (uids + selectors + text + viewport), `chrome_screenshot`, `chrome_evaluate` |
-| **Navigate**    | `chrome_navigate` (with optional `initScript` at `document_start`), `chrome_wait_for`          |
-| **Interact**    | `chrome_click`, `chrome_type`, `chrome_fill`, `chrome_key`, `chrome_hover`                     |
-| **Gesture**     | `chrome_drag` (HTML5 DataTransfer), `chrome_scroll` (wheel + momentum), `chrome_tap` (touch)   |
-| **Files**       | `chrome_upload_file` (no native picker; works with React/Vue/Angular file inputs)              |
-| **Observe**     | `chrome_list_console_messages`, `chrome_list_network_requests`, `chrome_get_network_request` (with response body) |
+[![npm version](https://img.shields.io/npm/v/pi-chrome.svg)](https://www.npmjs.com/package/pi-chrome)
+[![npm downloads](https://img.shields.io/npm/dm/pi-chrome.svg)](https://www.npmjs.com/package/pi-chrome)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)
 
-Each tool is documented inline in Pi — agents see the parameters and the gotchas (synthetic vs. trusted, autoplay gates, file picker limits) without trial-and-error.
+`pi-chrome` ships **20+ browser tools** for Pi agents, backed by a small MIT-licensed Chrome extension that runs inside the Chrome profile **you already use** — including every site you're already signed into.
 
 ---
 
@@ -101,16 +64,43 @@ You'll watch the agent jump to your GitHub tab and read the page — using **you
 
 ## Killer recipes (copy-paste into Pi)
 
-Each one assumes tabs you already have open + accounts you're already signed into.
+Each recipe assumes the relevant tab is already open in the Chrome you control.
 
 **PR triage**
-> Use chrome_tab list to find my GitHub notifications tab, snapshot it, summarize PRs needing my review.
+
+```text
+You:    "Use chrome_tab list to find my GitHub notifications tab, then summarize PRs needing my review today, sorted by staleness."
+Agent:  chrome_tab(list) → chrome_snapshot(uid:el-notifications) → chrome_evaluate(...)
+        ✓ 7 PRs waiting on you. 2 stale >3d (storage-rewrite, billing-v2).
+          1 just turned CI-green (api-keys-prune). Full sorted list below.
+You:    [pastes the list straight into Linear]
+```
 
 **Linear standup**
-> Open my Linear current cycle in the active tab, snapshot it, write a 5-bullet standup.
+
+```text
+You:    "Open my Linear current cycle in the active tab and write a 5-bullet standup."
+Agent:  chrome_tab(activate, urlIncludes:"linear.app") → chrome_snapshot(uid:el-cycle) → chrome_evaluate(...)
+        ✓ 5 in-progress, 2 blocked. Standup draft:
+          • Shipped: bridge auto-recover.   • In flight: trusted-mode retry path.
+          • Blocked: vendor portal CSP (waiting on infra).
+          • Next: benchmark v2.             • Risk: none today.
+You:    [drops it into #standup]
+```
 
 **Bug repro with evidence**
-> Open the staging app I'm already signed into, reproduce \<bug>, save a screenshot of each step under `./repro/`.
+
+```text
+You:    "Repro the checkout 500 on staging, save a screenshot at each step under ./repro/."
+Agent:  chrome_navigate(staging) → chrome_click(uid:el-add-to-cart) → chrome_screenshot(./repro/01-cart.png)
+        → chrome_click(uid:el-checkout) → chrome_list_network_requests() → chrome_screenshot(./repro/02-500.png)
+        ✓ POST /api/checkout → 500. Response body saved → ./repro/checkout-500.json
+          3 screenshots in ./repro/. Trigger: missing tax_id when cart contains digital goods.
+You:    [files the ticket with the folder attached]
+```
+
+<details>
+<summary><strong>More recipes</strong> (form auto-fill, admin cross-check, visual diff, auth-only data pull, network forensics, file upload)</summary>
 
 **Form auto-fill (no submit)**
 > Open the vendor portal, fill the new-vendor form from this JSON, stop before submit.
@@ -130,23 +120,65 @@ Each one assumes tabs you already have open + accounts you're already signed int
 **File upload through React**
 > Open the photo uploader, `chrome_upload_file` with `./fixtures/sample.png`, confirm preview rendered.
 
+</details>
+
 ---
 
-## Architecture
+## Why pi-chrome vs. Playwright / CDP / Selenium
+
+> Short version: **pi-chrome is primitives — "Playwright for the Chrome you're already signed into."** Not an agent loop. Plug it under any agent framework (Browser Use, Stagehand, LangGraph) or call its tools directly from a Pi agent. See [docs/COMPARISON.md](./docs/COMPARISON.md) for the full three-axis landscape (drivers, agents, cloud providers).
+
+|                                | **pi-chrome**                     | Playwright / Puppeteer        | CDP-based agents              | Selenium / WebDriver          |
+| ------------------------------ | --------------------------------- | ----------------------------- | ----------------------------- | ----------------------------- |
+| **Time from `pi install` → first useful action on your real account** | ~60s (load unpacked, `/chrome doctor`) | hours (script login, store creds, debug headless) | 30+ min (`--remote-debug` setup, attach) | hours (driver + login script) |
+| **Survives MFA / SSO without code** | ✅ already logged in              | ❌                             | ⚠️ if you re-auth             | ❌                             |
+| Uses your real signed-in Chrome | ✅ extension in your profile      | ❌ throwaway profile           | ⚠️ requires `--remote-debug`  | ❌ throwaway profile           |
+| Re-login required               | **Never**                         | Every run                     | Sometimes                     | Every run                     |
+| **Multiple agents drive the same Chrome at once** | ✅ shared bridge | ❌ port collisions             | ❌                             | ❌                             |
+| Watch agent work, live          | ✅ default; toggle quiet          | ❌ headless or new window      | ⚠️ debugger banner always     | ❌ new window                  |
+| Real browser-trusted clicks     | ✅ opt-in (`chrome clicks on`)    | ✅                             | ✅                             | ✅                             |
+| Network/console capture         | ✅ built-in                       | ✅                             | ✅                             | ⚠️ via extensions             |
+| **Honest result envelopes¹**    | ✅                                 | ⚠️                            | ❌                             | ❌                             |
+| Self-graded by built-in benchmark² | ✅ 38 primitives + 4 long-horizon | n/a                          | n/a                           | n/a                           |
+
+¹ Every action returns `pageMutated`, `defaultPrevented`, `elementVisible`, `occludedBy`, and `valueMatches` so the agent knows when a click didn't take effect — instead of looping blindly.
+² [`test-suite/`](./test-suite) is mode-aware: a synthetic-events tool is *expected* to fail clipboard. If you build a competing tool, send a PR with your scores. We benchmark in public.
+
+---
+
+## Honest results
 
+Most browser-automation libraries return `void` or a generic ack. `pi-chrome` returns a structured envelope on every interaction:
+
+```text
+chrome_click(occluded-button) →
+  "Clicked el-3 — pageMutated=false; occluded by <div#overlay>"
 ```
-  ┌──────────────────────┐                         ┌──────────────────────────┐
-  │  Pi agent (terminal) │  ─── http://127.0.0.1:17318 ─→  │ Chrome extension     │
-  │  chrome_* tools      │                         │ (your real profile)      │
-  └──────────┬───────────┘                         └─────────┬────────────────┘
-             │ same machine                                  │
-             ▼                                               ▼
-   Other Pi sessions                              Tabs you already have open
-   share the same bridge                          (signed in to GitHub,
-   automatically                                   Linear, Stripe, etc.)
+
+```text
+chrome_type(react-input, "hello") →
+  "Typed into el-7 — valueMatches=true; pageMutated=true"
 ```
 
-Multiple Pi sessions (planner / worker / audit) can all drive the same Chrome at once. The first session opens the local bridge; later sessions detect it and pipe their commands through.
+This is why agents using pi-chrome don't get stuck in retry loops on broken sites. They get the **reason** the action didn't land and can fix course in one turn.
+
+---
+
+## What an agent gets
+
+**20 tools**, grouped by job. Every one runs against your already-open tabs.
+
+| Category        | Tools                                                                                          |
+| --------------- | ---------------------------------------------------------------------------------------------- |
+| **Tabs**        | `chrome_tab` (list/new/activate/close/version), `chrome_launch`                                |
+| **Inspect**     | `chrome_snapshot` (uids + selectors + text + viewport), `chrome_screenshot`, `chrome_evaluate` |
+| **Navigate**    | `chrome_navigate` (with optional `initScript` at `document_start`), `chrome_wait_for`          |
+| **Interact**    | `chrome_click`, `chrome_type`, `chrome_fill`, `chrome_key`, `chrome_hover`                     |
+| **Gesture**     | `chrome_drag` (HTML5 DataTransfer), `chrome_scroll` (wheel + momentum), `chrome_tap` (touch)   |
+| **Files**       | `chrome_upload_file` (no native picker; works with React/Vue/Angular file inputs)              |
+| **Observe**     | `chrome_list_console_messages`, `chrome_list_network_requests`, `chrome_get_network_request` (with response body) |
+
+Each tool is documented inline in Pi — agents see the parameters and the gotchas (synthetic vs. trusted, autoplay gates, file picker limits) without trial-and-error.
 
 ---
 
@@ -166,9 +198,7 @@ Multiple Pi sessions (planner / worker / audit) can all drive the same Chrome at
 
 Per-call `trusted: true / false` on any input tool wins over the global mode.
 
----
-
-## Background / watch modes
+### Background / watch modes
 
 By default, every `chrome_*` call focuses Chrome and activates the target tab so you can **watch the agent work** — invaluable for demos, debugging, and first-time confidence.
 
@@ -180,51 +210,56 @@ By default, every `chrome_*` call focuses Chrome and activates the target tab so
 
 Per-call `background: true` wins over the session toggle.
 
----
+### Diagnostics
 
-## Honest results
+- `/chrome doctor` — single command: connectivity, extension version, bridge owner, version drift, MAIN-world helper injection, `chrome_evaluate("1+1") === 2`, fingerprint flags.
+- `/chrome onboard` — guided first-time setup.
+- `/chrome quiet status`, `/chrome clicks status` — current modes.
 
-Most browser-automation libraries return `void` or a generic ack. `pi-chrome` returns a structured envelope on every interaction:
+If the loaded Chrome extension is older than `pi-chrome` on disk, `/chrome doctor` tells you to reload it from `chrome://extensions`.
 
-```text
-chrome_click(occluded-button) →
-  "Clicked el-3 — pageMutated=false; occluded by <div#overlay>"
-```
+---
 
-```text
-chrome_type(react-input, "hello") →
-  "Typed into el-7 — valueMatches=true; pageMutated=true"
+## Architecture
+
+```
+  ┌──────────────────────┐                         ┌──────────────────────────┐
+  │  Pi agent (terminal) │  ─── http://127.0.0.1:17318 ─→  │ Chrome extension     │
+  │  chrome_* tools      │                         │ (your real profile)      │
+  └──────────┬───────────┘                         └─────────┬────────────────┘
+             │ same machine                                  │
+             ▼                                               ▼
+   Other Pi sessions                              Tabs you already have open
+   share the same bridge                          (signed in to GitHub,
+   automatically                                   Linear, Stripe, etc.)
 ```
 
-This is why agents using pi-chrome don't get stuck in retry loops on broken sites. They get the **reason** the action didn't land and can fix course in one turn.
+Multiple Pi sessions (planner / worker / audit) can all drive the same Chrome at once. The first session opens the local bridge; later sessions detect it and pipe their commands through.
 
 ---
 
-## Diagnostics
-
-- `/chrome doctor` — single command: connectivity, extension version, bridge owner, version drift, MAIN-world helper injection, `chrome_evaluate("1+1") === 2`, fingerprint flags.
-- `/chrome onboard` — guided first-time setup.
-- `/chrome quiet status`, `/chrome clicks status` — current modes.
-
-If the loaded Chrome extension is older than `pi-chrome` on disk, `/chrome doctor` tells you to reload it from `chrome://extensions`.
+## Built-in benchmark suite
 
----
+[`test-suite/`](./test-suite) is a benchmark for **any** browser-control agent (not just pi-chrome). It includes **38 primitive challenges** plus **4 hermetic BrowserGym-style long-horizon tasks**.
 
-## Composes with
+Scoring is **expected-outcome-by-mode**, not raw PASS count: each challenge has an expected verdict per mode (`synthetic`, `trusted`, `manual`) and a tool grades itself by whether its actual outcome matches the expected one. This avoids false equivalence between modes — a synthetic-events tool isn't supposed to satisfy a clipboard user-activation gate; matching that expectation is the pass.
 
-- **[pi-qq](https://www.npmjs.com/package/pi-qq)** — `/qq summarize what the active GitHub tab shows` without polluting the main transcript.
-- **[pi-bar](https://www.npmjs.com/package/pi-bar)** — when the agent scrapes large pages, watch the context-usage segment turn yellow → red as a signal to `/qq` for a recap.
-- **PR demo skills** — screenshots write to `.pi/chrome-screenshots/` so you can attach them to PR descriptions or demo bundles.
+Each challenge exposes `window.__verdict` / `window.__reason` / `window.__events` and a manifest entry with expected results per mode.
 
----
+```bash
+cd test-suite && python3 -m http.server 8765
+# open http://127.0.0.1:8765/ in the Chrome window pi-chrome controls
+```
 
-## Why an unpacked Chrome extension?
+Categories: `trusted-input`, `pointer-humanization`, `keyboard`, `activation-gates`, `scroll`, `drag-drop`, `clipboard`, `native-controls`, `frameworks`, `editing`, `dom-complexity`, `frames`, `files`, `observability`, `fingerprint`, `agent-safety`.
 
-`pi-chrome` cannot ship through the Chrome Web Store — a Web Store extension cannot talk to a local bridge controlled by another tool on the same machine. So it ships as a small MIT-licensed unpacked extension in [`extensions/chrome-profile-bridge/browser-extension/`](./extensions/chrome-profile-bridge/browser-extension). **Read the source before loading.** `/chrome doctor` reports the extension version and warns when it drifts from your installed `pi-chrome`.
+If you build a competing tool, please open a PR with your scores. We benchmark in public.
 
 ---
 
-## Security model
+## Security model & why unpacked
+
+**Unpacked on purpose.** A Web Store extension cannot talk to a local bridge controlled by another tool on the same machine — so pi-chrome ships its bridge as an inspectable, MIT-licensed folder you load once with Developer Mode. Every line is yours to read in [`extensions/chrome-profile-bridge/browser-extension/`](./extensions/chrome-profile-bridge/browser-extension). `/chrome doctor` reports the loaded extension version and warns when it drifts from your installed `pi-chrome`.
 
 The companion extension runs in the Chrome profile where you install it and has broad tab/scripting permissions. Only install it from a package source you trust.
 
@@ -238,22 +273,11 @@ There is no network exposure; the bridge binds to loopback only.
 
 ---
 
-## Built-in benchmark suite
-
-[`test-suite/`](./test-suite) is a benchmark for **any** browser-control agent (not just pi-chrome). It includes **38 primitive challenges** plus **4 hermetic BrowserGym-style long-horizon tasks**.
-
-Scoring is **expected-outcome-by-mode**, not raw PASS count: each challenge has an expected verdict per mode (`synthetic`, `trusted`, `manual`) and a tool grades itself by whether its actual outcome matches the expected one. This avoids false equivalence between modes — a synthetic-events tool isn't supposed to satisfy a clipboard user-activation gate; matching that expectation is the pass.
-
-Each challenge exposes `window.__verdict` / `window.__reason` / `window.__events` and a manifest entry with expected results per mode.
-
-```bash
-cd test-suite && python3 -m http.server 8765
-# open http://127.0.0.1:8765/ in the Chrome window pi-chrome controls
-```
-
-Categories: `trusted-input`, `pointer-humanization`, `keyboard`, `activation-gates`, `scroll`, `drag-drop`, `clipboard`, `native-controls`, `frameworks`, `editing`, `dom-complexity`, `frames`, `files`, `observability`, `fingerprint`, `agent-safety`.
+## Composes with
 
-If you build a competing tool, please open a PR with your scores. We benchmark in public.
+- **[pi-qq](https://www.npmjs.com/package/pi-qq)** — `/qq summarize what the active GitHub tab shows` without polluting the main transcript.
+- **[pi-bar](https://www.npmjs.com/package/pi-bar)** — when the agent scrapes large pages, watch the context-usage segment turn yellow → red as a signal to `/qq` for a recap.
+- **PR demo skills** — screenshots write to `.pi/chrome-screenshots/` so you can attach them to PR descriptions or demo bundles.
 
 ---
 
diff --git a/extensions/chrome-profile-bridge/browser-extension/manifest.json b/extensions/chrome-profile-bridge/browser-extension/manifest.json
index 58525e4..53f5418 100644
--- a/extensions/chrome-profile-bridge/browser-extension/manifest.json
+++ b/extensions/chrome-profile-bridge/browser-extension/manifest.json
@@ -1,7 +1,7 @@
 {
   "manifest_version": 3,
   "name": "Pi Chrome Connector",
-  "version": "0.14.9",
+  "version": "0.15.0",
   "description": "Lets Pi control tabs in Chrome via a local connector at 127.0.0.1.",
   "permissions": [
     "tabs",
diff --git a/package.json b/package.json
index d1f861f..b2d42e0 100644
--- a/package.json
+++ b/package.json
@@ -1,11 +1,11 @@
 {
 	"name": "pi-chrome",
-	"version": "0.14.9",
+	"version": "0.15.0",
 	"scripts": {
 		"version": "node scripts/sync-manifest-version.js",
 		"prepublishOnly": "node scripts/sync-manifest-version.js"
 	},
-	"description": "The de-facto browser automation toolkit for Pi agents. Drive your existing logged-in Chrome — no re-login, no throwaway profile, no CDP. 20+ tools (click, type, navigate, screenshot, network capture, file upload, drag, scroll, touch) + honest result envelopes + a built-in benchmark suite.",
+	"description": "Give a Pi agent your real, signed-in Chrome. No CDP, no throwaway profile, no re-login. 20+ tools (click, type, navigate, screenshot, network capture, file upload, drag, touch) with honest result envelopes — and a built-in browser-control benchmark suite.",
 	"keywords": [
 		"pi",
 		"pi-package",
@@ -36,6 +36,7 @@
 		"stagehand-alternative"
 	],
 	"license": "MIT",
+	"author": "tianrendong (Earendil Inc.)",
 	"homepage": "https://github.com/tianrendong/pi-chrome#readme",
 	"repository": {
 		"type": "git",