Remove explore.py — agent orchestrates search+chat workflow itself

explore.py was a hardcoded pipeline (search → chat) that:
- Did not pass search results to chat (independent server-side RAG)
- Took control away from the agent (no reasoning between steps)
- Always invoked expensive chat even when search was sufficient

AI coding agents are better orchestrators — they can inspect search
results, apply freshness annotations, Read() modified files, and
decide whether to invoke chat.py with reasoning between each step.

Removed explore.py and all references from SKILL.md, workflows.md,
query-patterns.md, agents/codealive-code-explorer.md.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: rodion-m

agents/codealive-code-explorer.md

@@ -70,5 +70,5 @@ Return a structured summary:
 - Always include file paths and line numbers in findings
 - If the first search returns no useful results, try at least 2 different query phrasings before concluding
 - If authentication fails, report the error and stop — do not retry
-- Do not use chat.py or explore.py — only search.py (to keep costs low)
+- Do not use chat.py — only search.py (to keep costs low)
 - Keep your response concise — the goal is to save the caller's context window

skills/codealive-context-engine/SKILL.md

@@ -41,7 +41,6 @@ Do NOT retry the failed script until setup completes successfully.
 | **Search** | `search.py` | Fast | Low | Finding code locations, descriptions, identifiers |
 | **Fetch Artifacts** | `fetch.py` | Fast | Low | Retrieving full content for search results |
 | **Chat with Codebase** | `chat.py` | Slow | High | Synthesized answers, architectural explanations |
-| **Explore** | `explore.py` | Slow | High | Multi-step discovery workflows |
 
 **Cost guidance:** Search is lightweight and should be the default starting point. Chat with Codebase invokes an LLM on the server side, making it significantly more expensive per call — use it when you need a synthesized, ready-to-use answer rather than raw search results.
 
@@ -93,13 +92,6 @@ python scripts/chat.py "Explain the authentication flow" my-backend
 python scripts/chat.py "What about security considerations?" --continue CONV_ID
 ```
 
-### 5. Multi-step exploration
-
-```bash
-python scripts/explore.py "understand:user authentication" my-backend
-python scripts/explore.py "debug:slow database queries" my-service
-```
-
 ## Tool Reference
 
 ### `datasources.py` — List Data Sources
@@ -158,22 +150,6 @@ python scripts/chat.py <question> <data_sources...> [options]
 
 **Conversation continuity:** Every response includes a `conversation_id`. Pass it with `--continue` for follow-up questions — this preserves context and is cheaper than starting fresh.
 
-### `explore.py` — Smart Exploration
-
-Combines search and chat-with-codebase in multi-step workflows. Useful for complex investigations.
-
-```bash
-python scripts/explore.py <mode:query> <data_sources...>
-```
-
-| Mode | Purpose |
-|------|---------|
-| `understand:<topic>` | Search + explanation |
-| `dependency:<library>` | Library usage and internals |
-| `pattern:<pattern>` | Cross-project pattern discovery |
-| `implement:<feature>` | Find similar features for guidance |
-| `debug:<issue>` | Trace symptom to root cause |
-
 ## Data Sources
 
 **Repository** — single codebase, for targeted searches:
@@ -240,7 +216,7 @@ This skill works standalone, but delivers the best experience when combined with
 | **This skill** | Query patterns, workflow guidance, cost-aware tool selection |
 | **MCP server** | Direct `codebase_search`, `fetch_artifacts`, `codebase_consultant`, `get_data_sources` tools |
 
-When both are installed, prefer the MCP server's tools for direct operations and this skill's scripts for guided multi-step workflows like `explore.py`.
+When both are installed, prefer the MCP server's tools for direct operations and this skill's scripts for guided workflows.
 
 ## Detailed Guides
 

skills/codealive-context-engine/references/query-patterns.md

@@ -221,11 +221,6 @@ Use when:
 2. `search.py` to find specific implementations
 3. `chat.py` again with more context
 
-**Explorer for Complex Workflows:**
-- Use `explore.py` for multi-step exploration
-- Automatically combines search and consultation
-- Specialized modes for different scenarios
-
 ## Anti-Patterns (Avoid These)
 
 ### Too Vague

skills/codealive-context-engine/references/workflows.md

@@ -106,12 +106,6 @@ python search.py "password reset, email verification, 2FA" my-backend
 ### Example: Adding Rate Limiting
 
 #### Step 1: Check for Existing Similar Features
-```bash
-python explore.py "implement:rate limiting" my-backend
-```
-
-OR manually:
-
 ```bash
 python search.py "rate limiting, request throttling, API quotas" my-backend workspace:all-backend
 ```
@@ -147,12 +141,6 @@ python chat.py "Based on existing patterns in the codebase, what's the recommend
 ### Example: Understanding axios Usage
 
 #### Step 1: Find All Usage
-```bash
-python explore.py "dependency:axios" my-frontend
-```
-
-OR manually:
-
 ```bash
 python search.py "axios import, axios.create, axios usage patterns" my-frontend --include-content
 ```
@@ -191,12 +179,6 @@ python chat.py "Compare axios vs fetch usage in our codebase. When is each used
 ### Example: Error Handling Patterns
 
 #### Step 1: Broad Search Across Workspace
-```bash
-python explore.py "pattern:error handling across microservices" workspace:backend-team
-```
-
-OR:
-
 ```bash
 python search.py "error handling patterns, exception middleware, error logging" workspace:backend-team --mode deep
 ```
@@ -227,12 +209,6 @@ python chat.py "What error handling anti-patterns exist in our codebase that we
 ### Example: Investigating Slow API Responses
 
 #### Step 1: Find Related Code
-```bash
-python explore.py "debug:slow API response times" my-api-service
-```
-
-OR:
-
 ```bash
 python search.py "API performance, slow queries, request handling" my-api-service --include-content
 ```
@@ -338,9 +314,9 @@ python search.py "deployment configuration, CI/CD, build process" new-service
 
 ```bash
 # Feature-by-feature exploration
-python explore.py "understand:user management" new-service
-python explore.py "understand:API integration" new-service
-python explore.py "understand:background jobs" new-service
+python search.py "user management" new-service --description-detail full
+python search.py "API integration" new-service --description-detail full
+python search.py "background jobs" new-service --description-detail full
 ```
 
 **Progressive Learning:** Overview → Core Features → Development Practices → Deep Dives