docs: rewrite README for plugin-first install

- Remove manual install and install.sh references
- Add prerequisites section (tmux, jq/python3)
- Add step to write a spec before running
- Fix "PRD" → "spec" in modes table
- Add --headless to options list
- Update generator description with startup sequence
- Note evaluator calibration examples

README.md

@@ -8,10 +8,7 @@ A generator-evaluator loop runs fresh Claude Code sessions per iteration. Each i
 
 ## Install
 
-### As a Claude Code Plugin (Recommended)
-
 ```
-/plugin marketplace add https://git.jagfly.com/sheldon/loop-loop.git
 /plugin install agent-loop@agent-loop
 ```
 
@@ -23,16 +20,18 @@ Then in any project:
 
 That's it. The single command handles setup, planning, and execution.
 
-### Manual Install
+## Prerequisites
 
-```bash
+- [Claude Code](https://docs.anthropic.com/en/docs/claude-code) CLI installed
-cp -r /path/to/loop-loop .loop
+- `tmux` available (used to run the loop in a detachable session)
-```
+- `jq` or `python3` (for JSON state management)
-
-Then run `.loop/loop.sh` directly.
 
 ## How It Works
 
+1. Write a spec describing what you want to build (`SPEC.md`, `docs/specs/*.md`, or similar)
+2. Run `/agent-loop:run` — it scaffolds `.loop/`, generates stories from your spec, and presents them for review
+3. Say "go" — the loop launches in tmux and runs autonomously
+
 ```
 /agent-loop:run
   ├─ Phase 1: Scaffold .loop/ (if needed)
@@ -50,7 +49,7 @@ Then run `.loop/loop.sh` directly.
 
 | Mode | What it does | Git writes? |
 |------|-------------|-------------|
-| **implement** | Build features from a PRD | Yes |
+| **implement** | Build features from a spec | Yes |
 | **explore** | Read-only codebase analysis | No |
 | **fix** | Targeted bug fixes / tech debt | Yes |
 
@@ -80,6 +79,7 @@ For CI or background execution without the interactive UI:
 ```bash
 .loop/loop.sh --headless [options]
 
+--headless                       Run without interactive UI
 --mode <implement|explore|fix>   Operating mode
 --max <N>                        Maximum iterations (default: 20)
 --skip-eval                      Skip evaluator pass
@@ -89,12 +89,12 @@ For CI or background execution without the interactive UI:
 ## Architecture
 
 ### Generator
-Fresh Claude Code session each iteration. Reads `prd.json` to find the highest-priority incomplete story, reads the sprint contract, implements the story, runs quality gates, commits, and marks it done.
+Fresh Claude Code session each iteration. Follows a strict startup sequence: reads progress.md, finds the next story from prd.json, reads the sprint contract, checks for evaluator feedback, reviews git history, and runs a smoke test if available — all before writing any code. Then implements the story, runs quality gates, commits, and marks it done.
 
 ### Evaluator
-Separate fresh session after each generator pass. Skeptically verifies the work: checks acceptance criteria against actual code, runs tests and the application, and issues a `PASS` or `REJECT` verdict. Rejection sends the story back with specific feedback.
+Separate fresh session after each generator pass. Skeptically verifies the work: checks each acceptance criterion against actual code with file paths and line numbers, runs tests, and issues a `PASS` or `REJECT` verdict. Rejection sends the story back with specific feedback.
 
-Evaluator skepticism is deliberately tuned — Claude's default tendency is to rationalize away issues. The evaluator prompt includes explicit bias correction.
+Evaluator skepticism is deliberately tuned — Claude's default tendency is to rationalize away issues. The evaluator prompt includes explicit bias correction and few-shot calibration examples.
 
 ### Sprint Contracts
 Before the loop starts, the planner generates contracts for each story. These define "done" conditions that both generator and evaluator reference, eliminating ambiguity about whether work is complete.