Tighten AGENTS.md: remove redundant content covered by Memory

Removed sections that duplicate Workspace Memory:
- Recommended Entry Points (Memory has precise file/line locations)
- For Debugging paths (Memory has session/error log details)
- Dependency Analysis Artifacts (reference info, not actionable)

Kept essential guardrails:
- Critical Invariants (MUST/MUST NOT rules)
- Dangerous Code Paths (risk warnings, not locations)
- Do/Dont coding standards
- Common Incorrect Assumptions

Reduction: 125 lines → 69 lines (~45% smaller, ~650 tokens saved)

AGENTS.md

@@ -1,7 +1,8 @@
 # AGENTS.md - Machine Instructions for g3
 
 **Purpose**: Machine-specific instructions for AI agents working with this codebase.  
-**For project overview, architecture, and usage**: See [README.md](README.md)
+**For code locations**: See Workspace Memory (loaded automatically)  
+**For project overview**: See [README.md](README.md)
 
 ## Critical Invariants
 
@@ -24,77 +25,35 @@
 4. **Never assume tool results fit in context** - Large results are thinned automatically
 5. **Never use byte-index string slicing on text with potential multi-byte characters** - Causes panics on emoji, CJK, box-drawing chars
 
-## Recommended Entry Points
+## Adding Features
 
-### For Understanding the System
+- **New tool**: Add definition in `tool_definitions.rs`, implement in `tools/`, add dispatch case
+- **New provider**: Implement `LLMProvider` trait in `g3-providers`
+- **New CLI mode**: Add to CLI args, implement handler in `g3-cli`
+- **New config option**: Add to `g3-config` structs
 
-1. `src/main.rs` - Entry point (trivial)
-2. `crates/g3-cli/src/lib.rs` - CLI logic and execution modes
-3. `crates/g3-core/src/lib.rs` - Agent struct and orchestration
-4. `crates/g3-providers/src/lib.rs` - Provider trait definition
+## Dangerous Code Paths
 
-### For Adding Features
+These areas have subtle bugs if modified incorrectly:
 
-1. **New tool**: `crates/g3-core/src/tool_definitions.rs` → `crates/g3-core/src/tools/`
-2. **New provider**: `crates/g3-providers/src/` → implement `LLMProvider` trait
-3. **New CLI mode**: `crates/g3-cli/src/lib.rs`
-4. **New config option**: `crates/g3-config/src/lib.rs`
+| Area | Risk |
+|------|------|
+| **Context window management** | Incorrect token estimates cause context overflow |
+| **Streaming parser** | Partial JSON across chunks causes parsing failures |
+| **Tool dispatch** | Missing dispatch cases cause silent failures |
+| **Retry logic** | Aggressive retries hit rate limits harder |
+| **Parser sanitization** | Inline JSON can trigger false tool call detection |
 
-### For Debugging
-
-1. Session logs: `.g3/sessions/<session_id>/session.json`
-2. Error logs: `.g3/errors/`
-3. Context state: Use `/stats` command in interactive mode
-
-## Dangerous/Subtle Code Paths
-
-### Context Window Management (`g3-core/src/context_window.rs`)
-
-- **Thinning**: Automatically replaces large tool results with file references
-- **Summarization**: Compresses conversation history at 80% capacity
-- **Token estimation**: Uses character-based heuristics, not exact tokenization
-- **Risk**: Incorrect token estimates can cause context overflow
-
-### Streaming Parser (`g3-core/src/streaming_parser.rs`)
-
-- Parses LLM responses in real-time for tool calls
-- Must handle partial JSON across chunk boundaries
-- **Risk**: Malformed responses can cause parsing failures
-
-### Tool Dispatch (`g3-core/src/tool_dispatch.rs`)
-
-- Routes tool calls to implementations
-- Handles both native and JSON-based tool calling
-- **Risk**: Missing dispatch cases cause silent failures
-
-### Retry Logic (`g3-core/src/retry.rs`)
-
-- Exponential backoff with jitter
-- Different configs for interactive vs autonomous mode
-- **Risk**: Aggressive retries can hit rate limits harder
-
-### Parser Sanitization (`g3-core/src/streaming_parser.rs`)
-
-- Sanitizes inline tool-call JSON patterns to prevent parser poisoning
-- Replaces `{` with fullwidth `｛` (U+FF5B) when patterns appear inline (not on their own line)
-- Real tool calls from LLMs always appear on their own line
-- **Risk**: Inline JSON examples in prose can trigger false tool call detection without sanitization
-
-## Do's and Don'ts for Automated Changes
+## Do's and Don'ts
 
 ### Do
-
 - ✅ Run `cargo check` after modifications
 - ✅ Run `cargo test` before committing
 - ✅ Update tool definitions when adding tools
 - ✅ Add tests for new functionality
-- ✅ Use existing patterns for similar features
 - ✅ Keep functions under 80 lines
-- ✅ Update documentation for user-facing changes
 
 ### Don't
-
-- ❌ Modify `Cargo.toml` dependencies without justification
 - ❌ Add blocking code in async contexts
 - ❌ Store sensitive data in plain text
 - ❌ Ignore error handling
@@ -108,18 +67,3 @@
 3. **"Tool results are always small"** - File reads can return megabytes
 4. **"Sessions persist across runs"** - Sessions are ephemeral by default
 5. **"All platforms are equal"** - macOS has more features (Vision, Accessibility)
-
-## Dependency Analysis Artifacts
-
-The `analysis/deps/` directory contains static analysis artifacts generated by the Euler agent:
-
-| File | Purpose |
-|------|--------|
-| `graph.json` | Raw dependency graph data (crate and file-level edges with evidence) |
-| `graph.summary.md` | Overview metrics: crate counts, edge counts, fan-in/fan-out rankings |
-| `sccs.md` | Strongly Connected Components analysis (cycle detection via Tarjan's algorithm) |
-| `layers.observed.md` | Mechanically-derived layer diagram showing crate hierarchy and intra-crate module structure |
-| `hotspots.md` | Coupling hotspots: files/crates with disproportionate fan-in or fan-out (>2× average) |
-| `limitations.md` | Known limitations of the static analysis (conditional compilation, macros, re-exports) |
-
-These artifacts are useful for understanding coupling, planning refactors, and identifying architectural boundaries.