@xcraftmind/mastermind 0.28.2 → 0.30.0

package/README.md

@@ -57,7 +57,7 @@ Three pieces — the split is the part that trips people up:
 | **MCP registration** — `setup claude` | once | `~/.claude.json` (via `claude mcp add`) | once for all projects |
 
 - **The index is always per-project.** Run `mastermind init` in *every* repo you want indexed. `doctor` reporting `index database not found` just means you haven't done this in the current directory yet (the exact situation if you run `doctor` from `/tmp` or a fresh shell).
-- **The workflow installs globally on `init`** — subagents, skills + slash commands land in `~/.claude/{agents,skills,commands}/`, overwriting Mastermind's own files to keep them current (`--no-global` to skip). Ships with the npm package; cargo installs use the plugin marketplace instead.
+- **The workflow installs globally on `init`** — subagents, skills + slash commands land in `~/.claude/{agents,skills,commands}/`, overwriting Mastermind's own files to keep them current (`--no-global` to skip). Ships with the npm package; a cargo install includes only the mmcg binary, not the workflow bundle.
 - **The MCP registration is usually once, globally.** The global entry launches `mastermind serve` from whichever project you open in Claude Code, so it picks up *that* project's `.mastermind/mmcg.db` automatically. You do **not** re-run `setup claude` per repo.
 - Use **per-project registration** only if you want the MCP config committed with the repo and version-pinned: `mastermind setup claude --project . --write-mcp` writes `./.mcp.json` with `command: "./node_modules/.bin/mastermind"` (pair it with a project-local install — see below).
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xcraftmind/mastermind",
-  "version": "0.28.2",
+  "version": "0.30.0",
   "description": "Mastermind workflow CLI + mmcg codegraph for AI coding agents — verify-spec / audit-spec gates, MCP server, multi-language tree-sitter indexer (Python, TypeScript, JavaScript, Rust, C#, Go, Java, PHP, C/C++). Prebuilt native binaries via optional platform packages — no Rust toolchain required.",
   "license": "MIT",
   "author": "xcraftmind",
@@ -38,12 +38,12 @@
     "mastermind"
   ],
   "optionalDependencies": {
-    "@xcraftmind/mmcg-darwin-arm64": "0.28.2",
-    "@xcraftmind/mmcg-darwin-x64": "0.28.2",
-    "@xcraftmind/mmcg-linux-x64-gnu": "0.28.2",
-    "@xcraftmind/mmcg-linux-arm64-gnu": "0.28.2",
-    "@xcraftmind/mmcg-linux-x64-musl": "0.28.2",
-    "@xcraftmind/mmcg-linux-arm64-musl": "0.28.2",
-    "@xcraftmind/mmcg-win32-x64-msvc": "0.28.2"
+    "@xcraftmind/mmcg-darwin-arm64": "0.30.0",
+    "@xcraftmind/mmcg-darwin-x64": "0.30.0",
+    "@xcraftmind/mmcg-linux-x64-gnu": "0.30.0",
+    "@xcraftmind/mmcg-linux-arm64-gnu": "0.30.0",
+    "@xcraftmind/mmcg-linux-x64-musl": "0.30.0",
+    "@xcraftmind/mmcg-linux-arm64-musl": "0.30.0",
+    "@xcraftmind/mmcg-win32-x64-msvc": "0.30.0"
   }
 }

package/share/agents/mastermind-auditor.md

@@ -1,8 +1,11 @@
 ---
 name: mastermind-auditor
 description: Independent post-flight auditor that mechanically verifies an executor's report against the actual repo state — git diff, file contents, VERIFY commands, mmcg_callers counts. Spawn from the planner after the executor returns, BEFORE telling the user "done". Adversarial to the report — verifies, does not trust.
+tools: Read, Grep, Glob, Bash
+model: opus
+mcpServers: [mmcg]
 metadata:
-  version: 0.4.0
+  version: 0.4.1
   authors:
     - mastermind
   tags:
@@ -10,12 +13,6 @@ metadata:
     - audit
     - mmcg
     - canons
-  model: opus
-  tools:
-    - Read
-    - Grep
-    - Glob
-    - Bash
 ---
 
 # Mastermind Auditor
@@ -304,6 +301,16 @@ On `❌ contract broken`:
 
 The `blocking_reason` must be a single sentence naming the concrete discrepancy — not "see audit" or "contract broken". It appears verbatim in `mastermind status` and `mastermind resume` output.
 
+## Final output self-check (REQUIRED — complete before ending your response)
+
+Before writing your last word, verify all three conditions:
+
+1. Does your response contain `<!-- mastermind:audit-begin -->`? If not, emit the full structured tail now.
+2. Does your response contain `<!-- mastermind:audit-end -->`? If not, close the block now.
+3. Is the YAML inside the block valid — `verdict:`, `discrepancies:`, `scope_match:` all present? If malformed, rewrite the block.
+
+A response without the sentinel block is **invalid** regardless of reasoning quality. The planner cannot route on prose alone.
+
 ## What you do NOT do
 
 - Run commands that modify state (no `git commit`, no `git push`, no destructive ops)

package/share/agents/mastermind-critic.md

@@ -1,8 +1,11 @@
 ---
 name: mastermind-critic
 description: Independent design-time challenger that stress-tests a proposed approach against 7 explicit engineering dimensions (correctness, performance, observability, non-breaking, YAGNI, AI slop, test/doc coverage) before it becomes a spec. Spawn from the planner during brainstorming — mandatory for sensitive areas. Distinct from `mastermind-auditor` which verifies post-execution.
+tools: Read, Grep, Glob
+model: opus
+mcpServers: [mmcg]
 metadata:
-  version: 0.4.0
+  version: 0.4.1
   authors:
     - mastermind
   tags:
@@ -10,11 +13,6 @@ metadata:
     - design
     - code-review
     - canons
-  model: opus
-  tools:
-    - Read
-    - Grep
-    - Glob
 ---
 
 # Critic — design-time challenger

package/share/agents/mastermind-investigator.md

@@ -1,8 +1,11 @@
 ---
 name: mastermind-investigator
 description: Sonnet-tier debugging subagent that structures root-cause investigations using a Hypothesis Ledger — tracks symptoms, known facts, competing hypotheses, evidence for/against each, and one focused next probe. Spawn from a planner when you have a bug or unexpected behavior with an unknown cause. Prevents premature closure by forcing evidence_against before any hypothesis can be confirmed.
+tools: Read, Grep, Glob, Bash
+model: sonnet
+mcpServers: [mmcg]
 metadata:
-  version: 0.1.0
+  version: 0.1.1
   authors:
     - mastermind
   tags:
@@ -10,12 +13,6 @@ metadata:
     - debugging
     - investigation
     - mmcg
-  model: sonnet
-  tools:
-    - Read
-    - Grep
-    - Glob
-    - Bash
 ---
 
 # Mastermind Investigator

package/share/agents/mastermind-prompt-refiner.md

@@ -1,16 +1,15 @@
 ---
 name: mastermind-prompt-refiner
 description: Intake gate that normalizes raw client prompts before the planner sees them. Converts brain dumps, vague ideas, and multi-intent requests into planner-ready input. Spawn whenever the user's request is rough, client-provided, or bundles multiple intents — skip when the request is already tight.
+tools: Read
+model: sonnet
 metadata:
-  version: 0.2.0
+  version: 0.2.1
   authors:
     - mastermind
   tags:
     - prompt-engineering
     - workflow
-  model: sonnet
-  tools:
-    - Read
 ---
 
 # Prompt Refiner — Intake Gate

package/share/agents/mastermind-researcher.md

@@ -1,20 +1,17 @@
 ---
 name: mastermind-researcher
 description: Read-only Haiku-tier subagent that explores the codebase, reads documentation, and returns structured fact summaries without making decisions. Spawn from a planner when you need to gather facts before designing — bulk grep/read/glob work that doesn't deserve Opus time. Use when you'd otherwise burn the main agent's context on "find all callsites of X" or "list all configs under Y".
+tools: Read, Grep, Glob, Bash
+model: haiku
+mcpServers: [mmcg]
 metadata:
-  version: 0.2.0
+  version: 0.2.1
   authors:
     - mastermind
   tags:
     - workflow
     - research
     - mmcg
-  model: haiku
-  tools:
-    - Read
-    - Grep
-    - Glob
-    - Bash
 ---
 
 # Researcher

package/share/agents/mastermind-task-executor.md

@@ -1,21 +1,16 @@
 ---
 name: mastermind-task-executor
 description: Subagent that executes a `.mastermind/tasks/<NNN>-<name>/spec.md` file phase-by-phase — applies edits, runs verification, marks the checklist, stops on first failure. Spawn this from a planner agent (using the [[mastermind-task-planning]] skill) to implement a delegated task.
+tools: Read, Edit, Write, Grep, Glob, Bash
+model: sonnet
+mcpServers: [mmcg]
 metadata:
-  version: 0.1.0
+  version: 0.1.1
   authors:
     - mastermind
   tags:
     - workflow
     - delegation
-  model: sonnet
-  tools:
-    - Read
-    - Edit
-    - Write
-    - Grep
-    - Glob
-    - Bash
 ---
 
 # Mastermind Task Executor

package/share/skills/mastermind-task-planning/references/defect-taxonomy.md

@@ -29,18 +29,17 @@ file as [`structured-report-schema.md`](structured-report-schema.md).
 
 - **What**: Spec's Phase 3 (docs) covers fewer files than
   `scripts/validate.py::validate_mmcg_tool_drift` enforces. Validator finds tool
-  names in `mcp.rs` but missing from one or more of: mmcg README, repo README,
-  `.claude-plugin/marketplace.json`, `plugins/mmcg/.claude-plugin/plugin.json`.
+  names in `mcp.rs` but missing from one or more of: mmcg README
+  (`mcp/servers/mmcg/README.md`), repo `README.md`.
 - **Surfaced as**: `python3 scripts/validate.py` exits non-zero with
   `tool 'mmcg_X' missing — declared in mcp/servers/mmcg/src/mcp.rs but absent
   from this file` (one error per missing surface).
-- **Fix template**: Add the three missing surfaces to `expected_docs[]` in the
-  spec frontmatter, then add three Phase 3.x sub-steps with FIND/CHANGE TO blocks.
-  Pattern: `marketplace.json` and `plugin.json` each carry ONE prose `description`
-  string with the comma-separated tool list and `N tools` count; the repo
-  `README.md` carries TWO occurrences (table cell + standalone-crate paragraph).
-  Insert the new tool name before the trailing `status` entry in each list and
-  bump the count by 1.
+- **Fix template**: Add the missing surface(s) to `expected_docs[]` in the
+  spec frontmatter, then add Phase 3.x sub-steps with FIND/CHANGE TO blocks.
+  Pattern: the mmcg `README.md` carries ONE comma-separated tool list plus an
+  `N tools` count; the repo `README.md` carries TWO occurrences (table cell +
+  standalone-crate paragraph). Insert the new tool name before the trailing
+  entry in each list and bump the count by 1.
 - **First observed**: Task 001 Phase 4.
 
 ### `zero_filter_verify`