ultimatehuman 0.1.1 → 0.1.3

package/LICENSING.md

@@ -34,7 +34,7 @@ Eligibility must hold while using the small-business permission. If the count re
 
 For business use outside the free permission, obtain a separate written agreement from **Vincent Wargnier**. Installation, configuration, and ongoing operation can be included in that agreement.
 
-[Request a commercial license or company installation](https://github.com/vincent38wargnier/ultimatehuman/issues/new?title=Commercial%20license%20inquiry). An inquiry does not grant a license. Keep credentials and confidential company information out of public issues.
+Email **[vincent@vw-coding.com](mailto:vincent@vw-coding.com)** to request a commercial license or company installation. An inquiry does not grant a license.
 
 Commercial agreements specify the customer, permitted use, deployment scope, fees, and any rights for contractors, hosting providers, resellers, or installers. The small-business permission does not authorize offering ultimatehuman itself as a commercial product or hosted service. It does not establish an exclusive right over every possible consulting or support service; any intended service-provider restrictions need to be addressed in the applicable agreement.
 

package/README.md

@@ -1,5 +1,5 @@
 <p align="center">
-  <img src="https://raw.githubusercontent.com/vincent38wargnier/ultimatehuman/main/docs/assets/hero.svg" alt="ultimatehuman — AI investigates. You decide." width="100%" />
+  <img src="https://raw.githubusercontent.com/vincent38wargnier/ultimatehuman/main/docs/assets/hero.svg" alt="ultimatehuman — 80× productivity. No AI slop. Proof before your attention. Runs on your Claude Code CLI subscription with $0 extra AI spend within its included usage. See the result's basis and cost details below." width="100%" />
 </p>
 
 <p align="center">
@@ -8,11 +8,30 @@
   <a href="https://github.com/vincent38wargnier/ultimatehuman/actions/workflows/check.yml"><img src="https://github.com/vincent38wargnier/ultimatehuman/actions/workflows/check.yml/badge.svg" alt="Build and package checks" /></a>
 </p>
 
-**Your production data already tells you where the product is breaking. ultimatehuman connects it to your code and brings you the investigation, the evidence, and a decision.**
+## Multiply your productivity by 80×.
 
-Run it on your machine. Set it up through chat. Watch the pipeline work. Review what deserves action.
+**Four months of AI-assisted work → one day of human decisions.**
 
-**Free for personal use and internal business use by companies with fewer than 2 employees. Businesses with 2 or more employees need a paid license for business use.** [Eligibility and commercial licensing](https://github.com/vincent38wargnier/ultimatehuman/blob/main/LICENSING.md)
+That is the result behind ultimatehuman. Vincent reports **about 100 tickets reviewed in 5 hours** in the founding workflow. The **80×** comparison uses 80 tickets at an estimated previous pace of one ticket per workday, compared with one day of human review. It compares human effort, not total engineering time, and is not a benchmark of this npm release.
+
+## No AI slop. By design.
+
+**AI cannot approve its own work.** It investigates the problem, checks the evidence, and brings you a decision. You inspect the case and accept, dismiss, or hold it.
+
+The public release delivers **investigation and human review**. The full workflow extends this to fixes, browser proof, and independent deployed verification; those stages are still being built. Evidence checks reduce unsupported findings; they are not a zero-defect guarantee.
+
+## Your existing CLI. Your existing subscription.
+
+**Runs on your Claude Code CLI. $0 extra AI spend within your subscription's included usage.** No second AI subscription or separate model API key is required.
+
+The engine reuses your local Claude Code login for chat and investigations. Work counts toward your existing plan's limits. Provider extra usage or a separately configured API key can incur charges. [Claude's billing explanation](https://support.claude.com/en/articles/12304248-manage-api-key-environment-variables-in-claude-code)
+
+Commercial licenses for ultimatehuman and any paid tracking or hosting services are separate. [License details](https://github.com/vincent38wargnier/ultimatehuman/blob/main/LICENSING.md)
+
+| CLI | Status |
+| --- | --- |
+| **Claude Code** | Available — reuses your local login |
+| **Codex CLI** | Planned — not implemented in this release |
 
 ## Start here
 
@@ -20,8 +39,12 @@ Run it on your machine. Set it up through chat. Watch the pipeline work. Review
 npx ultimatehuman@latest
 ```
 
+Run it locally. Set it up through chat. Watch **Pipeline live**. Make the call in **Review**.
+
 Requires **macOS or Linux**, **Node.js 22.13+**, **Git**, and **Claude Code installed and signed in**. [Install Node.js](https://nodejs.org/en/download) · [Set up Claude Code](https://code.claude.com/docs/en/quickstart)
 
+Free for personal use and internal business use with fewer than 2 employees. Business use with 2 or more employees requires a paid license. [License details](https://github.com/vincent38wargnier/ultimatehuman/blob/main/LICENSING.md) · [Contact Vincent](mailto:vincent@vw-coding.com)
+
 The CLI verifies your existing Claude account, starts the local engine, and opens your browser. **Continue in Chat.** Chat and investigations use your configured Claude Code account and count toward its usage limits.
 
 Start with something like:
@@ -35,13 +58,17 @@ Start with something like:
 
 Run the same command again to reopen your workspace. Your repositories, settings, and conversation are preserved.
 
-## Less chasing. More deciding.
+## How the evidence reaches you
 
-A log is a symptom. A replay is a clue. A repository explains how the failure could happen. Putting those pieces together is the work.
+Your production data tells you where the product is breaking. ultimatehuman connects those signals to your code and prepares a case you can inspect.
 
-ultimatehuman runs that investigation for you: it groups signals, reads the relevant code, challenges the explanation, and checks the evidence before a finding reaches your review queue. If the evidence does not hold up, the pipeline can finish without a finding.
+| Step | What happens |
+| --- | --- |
+| **01 · AI investigates** | Groups related signals, reads the relevant code, and explains the suspected cause. |
+| **02 · The pipeline requires evidence** | Challenges the explanation and checks the configured evidence requirements before filing a finding. |
+| **03 · You decide** | Inspect the problem, impact, and evidence. Accept, dismiss, or hold the finding. |
 
-**The AI does not approve its own work. You make the decision.**
+If the evidence does not hold up, a run can finish without a finding. Accepting one records your decision; it does not automatically merge or deploy code.
 
 <p align="center">
   <img src="https://raw.githubusercontent.com/vincent38wargnier/ultimatehuman/main/docs/assets/pipeline.svg" alt="Production signals and repository code flow through investigation and evidence checks to a human review." width="100%" />
@@ -88,7 +115,7 @@ The original Review viewer opens each screenshot at full size, with navigation b
 
 [View the checkout screenshot](https://github.com/vincent38wargnier/ultimatehuman/blob/main/docs/assets/screenshots/checkout-failure.png) · [View the request trace](https://github.com/vincent38wargnier/ultimatehuman/blob/main/docs/assets/screenshots/checkout-request.png)
 
-**Example scope:** these attachments come from a local demo. Version `0.1.0` does not yet connect screenshot attachments to review tickets or capture them automatically. The shipped release records investigation decisions; automated fixes and merges are future stages. [Screenshot details](https://github.com/vincent38wargnier/ultimatehuman/blob/main/docs/assets/screenshots/README.md)
+**Example scope:** these attachments come from a local demo. The current release does not yet connect screenshot attachments to review tickets or capture them automatically. The shipped release records investigation decisions; automated fixes and merges are future stages. [Screenshot details](https://github.com/vincent38wargnier/ultimatehuman/blob/main/docs/assets/screenshots/README.md)
 
 ## Start with the tools you already use
 
@@ -143,6 +170,10 @@ Prefer a persistent command? Run `npm install -g ultimatehuman`, then `ultimateh
 
 **Do I need a separate API key for Claude?** No. The normal installation uses your existing Claude Code login. Tracker credentials are separate and are requested only when connecting a source.
 
+**Does it add an AI bill?** With subscription login, work within your plan's included usage has no additional AI charge. Your existing limits still apply; provider extra usage and API-key billing are separate. ultimatehuman's commercial license and third-party services may also carry costs.
+
+**Can I use Codex CLI?** Not yet. The current installer, chat, and pipeline runner require Claude Code. Codex support is [planned](https://github.com/vincent38wargnier/ultimatehuman/blob/main/ROADMAP.md#v2-not-scheduled).
+
 **Can one project include several repositories?** Yes. Tell chat which repositories belong together, such as your frontend and API.
 
 **Do I need PostHog or Datadog?** No. The Security check works from repository code. Production bug investigations need a connected source with relevant data.
@@ -157,6 +188,10 @@ This is an early source-available release. Useful bug reports include the instal
 
 [Report a problem](https://github.com/vincent38wargnier/ultimatehuman/issues) · [Contribute](https://github.com/vincent38wargnier/ultimatehuman/blob/main/CONTRIBUTING.md) · [Run from source](https://github.com/vincent38wargnier/ultimatehuman/blob/main/docs/development.md) · [Agent installation guide](https://github.com/vincent38wargnier/ultimatehuman/blob/main/docs/agent-install.md)
 
+## Talk to the founder
+
+Questions, company installation, or commercial licensing: **[vincent@vw-coding.com](mailto:vincent@vw-coding.com)** — Vincent Wargnier, VW Coding.
+
 ## License and commercial use
 
 Source-available under the [ultimatehuman Community License 1.0](https://github.com/vincent38wargnier/ultimatehuman/blob/main/LICENSE). This combines PolyForm Noncommercial 1.0.0 with an additional permission for qualifying small businesses. It is a custom license, not MIT or an OSI-approved open-source license.
@@ -170,6 +205,6 @@ Source-available under the [ultimatehuman Community License 1.0](https://github.
 
 Count employees across the business and its controlled group, not just ultimatehuman users. Part-time employees count as one person; founders count if they are employees. Work on a client's projects uses the client's headcount too. If the business grows to 2 employees, obtain a commercial license before continuing business use. The underlying license's specified nonprofit, educational, research, and government permissions remain available.
 
-[Request a commercial license or company installation from Vincent Wargnier](https://github.com/vincent38wargnier/ultimatehuman/issues/new?title=Commercial%20license%20inquiry).
+[Contact Vincent Wargnier for a commercial license or company installation](mailto:vincent@vw-coding.com).
 
 Previously granted rights remain valid, including the earlier Apache-licensed revisions. [Eligibility examples, previous versions, and third-party licenses](https://github.com/vincent38wargnier/ultimatehuman/blob/main/LICENSING.md)

package/dist/cli.mjs

@@ -32628,13 +32628,14 @@ async function service(sub, flags) {
 // packages/cli/package.json
 var package_default = {
   name: "ultimatehuman",
-  version: "0.1.1",
+  version: "0.1.3",
   private: false,
   files: ["dist", "LICENSE", "NOTICE", "LICENSING.md", "THIRD_PARTY_NOTICES.txt"],
   engines: { node: ">=22.13.0" },
   os: ["darwin", "linux"],
   type: "module",
-  description: "AI investigates. You decide. Turn production signals and repository code into evidence-backed engineering reviews, using Claude Code.",
+  description: "No AI slop. Proof before human review. Runs on your existing Claude Code subscription, within its included usage. Read the founder's 80\xD7 productivity case.",
+  author: { name: "Vincent Wargnier", email: "vincent@vw-coding.com" },
   license: "SEE LICENSE IN LICENSE",
   repository: {
     type: "git",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ultimatehuman",
-  "version": "0.1.1",
+  "version": "0.1.3",
   "files": [
     "dist",
     "LICENSE",
@@ -16,7 +16,11 @@
     "linux"
   ],
   "type": "module",
-  "description": "AI investigates. You decide. Turn production signals and repository code into evidence-backed engineering reviews, using Claude Code.",
+  "description": "No AI slop. Proof before human review. Runs on your existing Claude Code subscription, within its included usage. Read the founder's 80× productivity case.",
+  "author": {
+    "name": "Vincent Wargnier",
+    "email": "vincent@vw-coding.com"
+  },
   "license": "SEE LICENSE IN LICENSE",
   "repository": {
     "type": "git",