docs: update CLAUDE.md for recently merged features (#183)

* docs: update CLAUDE.md for recently merged features

Document skills system, sandbox network proxy, leak detector,
Tinfoil private inference, setup wizard, and shell env scrubbing
that were merged but not reflected in CLAUDE.md.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* docs: fix SKILL.md format example and scoring description

Align SKILL.md frontmatter example with actual SkillManifest struct:
activation block with patterns/keywords/max_context_tokens, requires
nested under metadata.openclaw. Fix scoring pipeline description to
mention keywords, tags, and regex patterns instead of triggers/intents.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* docs: optimize CLAUDE.md structure and reduce from 959 to 671 lines

- Update llm/ directory tree (4 -> 12 files to match actual codebase)
- Fix "NEAR AI (required)" -> "NEAR AI (when LLM_BACKEND=nearai)"
- Remove 28-item Completed changelog list (no actionable value)
- Deduplicate 3 config blocks with cross-references
- Extract Workspace deep-dive to src/workspace/README.md
- Extract Tool Architecture deep-dive to src/tools/README.md
- Consolidate Code Style and Review Discipline under Key Patterns
- Add workspace and tools to Module Specifications table

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>

src/workspace/README.md

@@ -0,0 +1,111 @@
+# Workspace & Memory System
+
+Inspired by [OpenClaw](https://github.com/openclaw/openclaw), the workspace provides persistent memory for agents with a flexible filesystem-like structure.
+
+## Key Principles
+
+1. **"Memory is database, not RAM"** - If you want to remember something, write it explicitly
+2. **Flexible structure** - Create any directory/file hierarchy you need
+3. **Self-documenting** - Use README.md files to describe directory structure
+4. **Hybrid search** - Combines FTS (keyword) + vector (semantic) via Reciprocal Rank Fusion
+
+## Filesystem Structure
+
+```
+workspace/
+├── README.md              <- Root runbook/index
+├── MEMORY.md              <- Long-term curated memory
+├── HEARTBEAT.md           <- Periodic checklist
+├── IDENTITY.md            <- Agent name, nature, vibe
+├── SOUL.md                <- Core values
+├── AGENTS.md              <- Behavior instructions
+├── USER.md                <- User context
+├── context/               <- Identity-related docs
+│   ├── vision.md
+│   └── priorities.md
+├── daily/                 <- Daily logs
+│   ├── 2024-01-15.md
+│   └── 2024-01-16.md
+├── projects/              <- Arbitrary structure
+│   └── alpha/
+│       ├── README.md
+│       └── notes.md
+└── ...
+```
+
+## Using the Workspace
+
+```rust
+use crate::workspace::{Workspace, OpenAiEmbeddings, paths};
+
+// Create workspace for a user
+let workspace = Workspace::new("user_123", pool)
+    .with_embeddings(Arc::new(OpenAiEmbeddings::new(api_key)));
+
+// Read/write any path
+let doc = workspace.read("projects/alpha/notes.md").await?;
+workspace.write("context/priorities.md", "# Priorities\n\n1. Feature X").await?;
+workspace.append("daily/2024-01-15.md", "Completed task X").await?;
+
+// Convenience methods for well-known files
+workspace.append_memory("User prefers dark mode").await?;
+workspace.append_daily_log("Session note").await?;
+
+// List directory contents
+let entries = workspace.list("projects/").await?;
+
+// Search (hybrid FTS + vector)
+let results = workspace.search("dark mode preference", 5).await?;
+
+// Get system prompt from identity files
+let prompt = workspace.system_prompt().await?;
+```
+
+## Memory Tools
+
+Four tools for LLM use:
+
+- **`memory_search`** - Hybrid search, MUST be called before answering questions about prior work
+- **`memory_write`** - Write to any path (memory, daily_log, or custom paths)
+- **`memory_read`** - Read any file by path
+- **`memory_tree`** - View workspace structure as a tree (depth parameter, default 1)
+
+## Hybrid Search (RRF)
+
+Combines full-text search and vector similarity using Reciprocal Rank Fusion:
+
+```
+score(d) = Σ 1/(k + rank(d)) for each method where d appears
+```
+
+Default k=60. Results from both methods are combined, with documents appearing in both getting boosted scores.
+
+**Backend differences:**
+- **PostgreSQL:** `ts_rank_cd` for FTS, pgvector cosine distance for vectors, full RRF
+- **libSQL:** FTS5 for keyword search only (vector search via `libsql_vector_idx` not yet wired)
+
+## Heartbeat System
+
+Proactive periodic execution (default: 30 minutes):
+
+1. Reads `HEARTBEAT.md` checklist
+2. Runs agent turn with checklist prompt
+3. If findings, notifies via channel
+4. If nothing, agent replies "HEARTBEAT_OK" (no notification)
+
+```rust
+use crate::agent::{HeartbeatConfig, spawn_heartbeat};
+
+let config = HeartbeatConfig::default()
+    .with_interval(Duration::from_secs(60 * 30))
+    .with_notify("user_123", "telegram");
+
+spawn_heartbeat(config, workspace, llm, response_tx);
+```
+
+## Chunking Strategy
+
+Documents are chunked for search indexing:
+- Default: 800 words per chunk (roughly 800 tokens for English)
+- 15% overlap between chunks for context preservation
+- Minimum chunk size: 50 words (tiny trailing chunks merge with previous)