Metadata-Version: 2.4
Name: tlm-cli
Version: 0.2.4
Summary: TLM — AI Tech Lead that enforces TDD, tests, and spec compliance in Claude Code.
Author-email: TLM <hello@tlmforge.dev>
License-Expression: MIT
Project-URL: Homepage, https://tlmforge.dev
Project-URL: Source, https://github.com/tlm-dev/tlm
Classifier: Development Status :: 4 - Beta
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Quality Assurance
Classifier: Intended Audience :: Developers
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: httpx>=0.27
Requires-Dist: click>=8.0
Requires-Dist: rich>=13.0
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.24; extra == "dev"
Requires-Dist: respx>=0.22; extra == "dev"

# TLM — AI Tech Lead for Claude Code

> The annoying agent that makes Claude do the right thing.

TLM sits inside [Claude Code](https://claude.ai/code) and enforces TDD, tests, and spec compliance — automatically. It scans your project, identifies gaps, and hooks into Claude to enforce quality.

## Quick Start

```bash
pipx install tlm-cli
tlm auth <your-api-key>
cd your-project
tlm install
```

That's it. Open Claude Code and start working — TLM activates automatically.

## What Happens

1. **`tlm auth <key>`** — Save your API key (one-time)
2. **`tlm install`** — Scans your project, sends to server for assessment, shows gaps, selects quality tier, installs Claude Code hooks
3. **Work in Claude Code** — TLM interviews you before features, enforces TDD, blocks deploys, warns on gaps
4. **`tlm check`** — Manual quality gate before deployment

## How It Works

TLM scans your project and sends the file tree + samples to the server for assessment. The server returns recommendations (gaps) ranked by severity:

```
Phase 5: Project Gaps (4 found)
┌──────────────────────────────────────────┐
│ critical  CI/CD      No CI/CD pipeline   │
│ critical  Testing    No tests found      │
│ high      Infra      No staging env      │
│ medium    Ops        No monitoring       │
└──────────────────────────────────────────┘
```

You choose a quality tier (high/standard/relaxed) and TLM enforces accordingly.

## Commands

| Command | What it does |
|---------|-------------|
| `tlm auth <key>` | Save API key |
| `tlm install` | Full setup: scan, assess, quality tier, gaps, hooks |
| `tlm scan` | Re-scan and show recommendations |
| `tlm gaps` | Show active project gaps |
| `tlm check` | Run quality gate before deploy |

## Quality Tiers

| Tier | Behavior |
|------|----------|
| **HIGH** | Block on any gap. Spec review required. Multi-model code review. |
| **STANDARD** | Block on critical gaps. Spec review on blockers. Single-model review. |
| **RELAXED** | Warn only. No spec blocking. Mechanical checks only. |

## Hooks

TLM installs 6 Claude Code hooks:

- **session_start** — Loads project context, gaps, quality rules
- **prompt_submit** — Phase-specific guidance, gap warnings
- **guard** (Write/Edit) — Blocks code during interview, enforces TDD
- **compliance** (Bash) — Review gate on git commit
- **deployment** (Bash) — Always blocks deploys until `tlm check` passes
- **stop** — Session cleanup

## License

MIT
