Release 0.7.2

Add three convenience MCP tools (install_package, search_log, inspect_data),
an on-demand Stata reference library under skills/stata-code/references/, and
a deterministic skill-zip packaging script. Bump all release version literals
0.7.1 → 0.7.2 and refresh the plugin tool count (15 → 18).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Author: brycewang-stanford

.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "Agent-native Stata bridge — MCP server, Jupyter kernel, and VS Code extension sharing one v1.0 result schema.",
-    "version": "0.7.1"
+    "version": "0.7.2"
   },
   "plugins": [
     {
       "name": "stata-code",
       "source": ".",
       "description": "Run Stata code from Claude Code through the stata-code MCP server (typed errors, token-economy logs/graphs, multi-session) and an agent skill that teaches Claude the result schema and Stata workflows.",
-      "version": "0.7.1",
+      "version": "0.7.2",
       "author": {
         "name": "Bryce Wang",
         "email": "brycewang@stanford.edu",

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "stata-code",
-  "version": "0.7.1",
-  "description": "Agent-native Stata bridge for Claude Code. Bundles an MCP server (15 tools, token-economy result schema, typed errors, multi-session) and an agent skill that teaches Claude how to call it idiomatically.",
+  "version": "0.7.2",
+  "description": "Agent-native Stata bridge for Claude Code. Bundles an MCP server (18 tools, token-economy result schema, typed errors, multi-session) and an agent skill with an on-demand Stata reference library that teaches Claude how to call it idiomatically.",
   "author": {
     "name": "Bryce Wang",
     "email": "brycewang@stanford.edu",

CHANGELOG.md

@@ -6,6 +6,33 @@ to semver-major.minor for the result schema (see `SCHEMA.md` §6).
 
 ## Unreleased
 
+## 0.7.2 — 2026-06-20
+
+### Added
+
+- **Three convenience MCP tools** raise the tool surface from 15 to 18:
+  - `install_package(name, source?, url?, replace?, session_id?)` — installs a
+    community package via `ssc install` / `net install` without the agent
+    having to remember the syntax, then verifies it resolves with `which`.
+    Package names and URLs are validated to keep them out of the generated
+    command line; failures surface the typed `error` block (e.g. `network`).
+  - `search_log(ref, pattern, is_regex?, ignore_case?, context?, max_matches?)`
+    — greps within a truncated `log://` payload and returns only the matching
+    lines (with optional context), so a long log can be inspected without
+    pulling the whole transcript back through `get_log`.
+  - `inspect_data(varlist?, detail?, session_id?)` — runs `describe` +
+    `codebook` and returns the structured `dataset` block plus the codebook
+    log: a one-call "what's in this dataset" the agent doesn't have to spell out.
+- **On-demand Stata reference library** under `skills/stata-code/references/`
+  (~4,200 lines): topic files for core syntax, data management, econometrics,
+  causal inference, panel/time series, graphics, and table export; load-bearing
+  `error-codes.md` (the full `rc → kind → fix` table + self-repair loop, aligned
+  with the typed-error taxonomy) and `defensive-coding.md`; and per-package notes
+  for `reghdfe`, `coefplot`, `estout`, and `gtools`. `SKILL.md` gained a routing
+  table (read 1–3 files on demand) and a live-vs-offline execution-mode section.
+- **`scripts/build_skill_zip.py`** packages the skill into a deterministic
+  `build/stata-code-skill.zip` for upload as Claude.ai project knowledge.
+
 ## 0.7.1 — 2026-06-19
 
 ### Fixed

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "stata-code"
-version = "0.7.1"
+version = "0.7.2"
 description = "Agent-native Stata bridge — one core, multiple frontends (MCP, Jupyter, VSCode)"
 readme = "README.md"
 license = "MIT"

stata_code/__init__.py

@@ -174,7 +174,7 @@ def is_available() -> bool:
     return True
 
 
-__version__ = "0.7.1"
+__version__ = "0.7.2"
 
 __all__ = [
     # Primary entry points

stata_code/mcp/server.py

@@ -98,7 +98,7 @@
 )
 from stata_code.core.schema import RunResult
 
-__version__ = "0.7.1"
+__version__ = "0.7.2"
 
 SERVER_INSTRUCTIONS = (
     "Use stata-code for running and inspecting Stata code. Prefer structuredContent "

vscode/package-lock.json

@@ -2,7 +2,7 @@
   "name": "stata-code-vscode",
   "displayName": "stata-code",
   "description": "Run Stata code from VSCode through the agent-native stata-code MCP server.",
-  "version": "0.7.1",
+  "version": "0.7.2",
   "publisher": "brycewang-stanford",
   "license": "MIT",
   "icon": "icon.png",