feat(tools): add WebScrapeExecutor with scrape-core integration (#99)

* feat(tools): add WebScrapeExecutor with scrape-core integration (#57)

Implement safe HTML scraping via scrape-core with CSS selectors:

- WebScrapeExecutor: fetch HTTPS URLs, parse HTML with Soup, extract
  data using CSS selectors (text, html, attr modes) in spawn_blocking
- CompositeExecutor<A, B>: generic first-match-wins executor chaining
  that preserves Agent's single ToolExecutor generic parameter
- SSRF protection: HTTPS-only, IPv4/IPv6 private IP blocking including
  link-local, unique local, IPv4-mapped, broadcast, unspecified
- Bundled web-scrape skill with CSS selector examples
- Shared extract_fenced_blocks() utility (DRY refactor from shell.rs)
- Config: [tools.scrape] with timeout (15s) and max_body_bytes (1MB)

Closes #57 Phase 2

* chore: bump version to 0.7.1, update CHANGELOG and README for web scrape

Author: bug-ops

CHANGELOG.md

@@ -6,6 +6,19 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
 ## [Unreleased]
 
+## [0.7.1] - 2026-02-09
+
+### Added
+- `WebScrapeExecutor`: safe HTML scraping via scrape-core with CSS selectors, SSRF protection, and HTTPS-only enforcement (Issue #57)
+- `CompositeExecutor<A, B>`: generic executor chaining with first-match-wins dispatch
+- Bundled `web-scrape` skill with CSS selector examples for structured data extraction
+- `extract_fenced_blocks()` shared utility for fenced code block parsing (DRY refactor)
+- `[tools.scrape]` config section with timeout and max body size settings
+
+### Changed
+- Agent tool output label from `[shell output]` to `[tool output]`
+- `ShellExecutor` block extraction now uses shared `extract_fenced_blocks()`
+
 ## [0.7.0] - 2026-02-08
 
 ### Added