claude-comms 1.0.13 → 1.0.15

package/.claude/agents/core/agent-orchestrator.md

@@ -35,7 +35,7 @@ You are a master strategist with decades of experience orchestrating complex sof
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)

package/.claude/agents/core/architect.md

@@ -71,7 +71,7 @@ Define system shape, boundaries, interfaces, testing strategies, and technology
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)

package/.claude/agents/core/business-analyst.md

@@ -48,7 +48,7 @@ Your core competencies include:
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)

package/.claude/agents/core/deep-researcher.md

@@ -96,7 +96,7 @@ COMPLETION GATE: Research Deliverables Checklist:
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)

package/.claude/agents/core/designer.md

@@ -100,7 +100,7 @@ COMPLETION GATE: Design Delivery Checklist:
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)

package/.claude/agents/core/engineer.md

@@ -66,7 +66,7 @@ You approach every task with the mindset: "If it's not tested, it's broken." Tes
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)
@@ -168,11 +168,11 @@ Populate your initial Todos with your step by step WORKFLOW:
    - Check for code duplication and extract common patterns
 
 6. **Validation & Coverage**:
-   - Run full test suite with `pnpm test` or appropriate command
+   - Run full test suite with appropriate command
    - Analyze coverage reports, ensure >80% for new code
-   - Run lint with `pnpm lint` and fix all issues
-   - Run build with `pnpm build` to verify compilation
-   - Run dev with `pnpm dev` to check runtime behavior
+   - Run lint command and fix all issues
+   - Run build command to verify compilation
+   - Run dev server to check runtime behavior
    - For UI changes, use Playwright to capture screenshots and verify visually
    - Ensure NO regressions - all existing tests must still pass
    - Broadcast final test/build status
@@ -193,10 +193,10 @@ COMPLETION GATE: MANDATORY Completion Criteria checklist:
 □ E2E tests cover critical user paths
 □ All acceptance criteria have passing tests
 □ Business Logic from source of truth specs fully tested
-□ `pnpm lint` runs without errors
-□ `pnpm test` runs fully green
-□ `pnpm build` completes without errors
-□ `pnpm dev` starts without issues
+□ lint command runs without errors
+□ tests run fully green
+□ project builds without errors
+□ dev server starts without issues
 □ NO regressions introduced (all existing tests pass)
 □ Code documented with clear comments
 □ Test plan documented in docs/project/phases/<phase-id>/
@@ -226,10 +226,10 @@ Brief overview of the feature/fix implemented, the TDD approach taken, and key o
 - Critical paths covered: [list key scenarios]
 
 ## Build & Test Status
-- `pnpm lint`: [PASS/FAIL] [details if fail]
-- `pnpm test`: [PASS/FAIL] [number passing/total]
-- `pnpm build`: [PASS/FAIL] [details if fail]
-- `pnpm dev`: [PASS/FAIL] [details if fail]
+- lint command: [PASS/FAIL] [details if fail]
+- test suite: [PASS/FAIL] [number passing/total]
+- build command: [PASS/FAIL] [details if fail]
+- dev server: [PASS/FAIL] [details if fail]
 
 ## Implementation Decisions
 Key technical decisions and rationale:

package/.claude/agents/core/gatekeeper.md

@@ -36,11 +36,11 @@ Populate your initial Todos with your step by step WORKFLOW:
    - Read entire modified files to understand complete implementation context
 
 2. **Automated Verification Suite Execution**
-   - Run `pnpm lint` → capture all errors and warnings with file references
-   - Run `pnpm test` with verbose output → analyze coverage and failures
-   - Run `pnpm build` → monitor for compilation errors and bundle issues
-   - Run `pnpm dev` → verify development environment stability
-   - Run security scanning tools if available (npm audit, etc.)
+   - Run lint command → capture all errors and warnings with file references
+   - Run test suite with verbose output → analyze coverage and failures
+   - Run build command → monitor for compilation errors and bundle issues
+   - Run dev server → verify development environment stability
+   - Run security scanning tools if available (dependency audit, etc.)
    - PONDER the severity and impact of any failures discovered
    - Document all technical check results with specific error details
 
@@ -236,7 +236,7 @@ COMPLETION GATE: MANDATORY Quality Checklist:
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)

package/.claude/agents/core/planner.md

@@ -64,7 +64,7 @@ Your expertise encompasses:
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)

package/.claude/agents/meta-agent-builder.md

@@ -182,10 +182,10 @@ Batch an Inbox Check with every step
    5. Test -> Code -> Test -> Repeat. Itterate until green!
 
 COMPLETION GATE: MANDITORY Completion Criteria checklist:
-□ `pnpm lint` needs to run without errors.
-□ `pnpm dev` needs to run without errors.
-□ `pnpm test` needs to run green.  
-□ `pnpm build` without errors.
+□ lint command needs to run without errors.
+□ dev server needs to run without errors.
+□ tests need to run green.  
+□ project builds without errors.
 □ No regressions introduced
 
 [/WORKFLOW]
@@ -204,10 +204,10 @@ Batch an Inbox Check with every step
    6. Update project level documentation like READMEs, docs/project/guides/ to reflect actual changes.
 
 REPORT back to the user the status of each:
-□ `pnpm lint`
-□ `pnpm dev`
-□ `pnpm test`  
-□ `pnpm build`
+□ lint command
+□ dev server
+□ tests  
+□ project builds
 □ Implementation meets requirements spec.
 □ Test coverage of Business logic and user flows.
 □ Implementation Review, Feedback, Critique.
@@ -293,7 +293,7 @@ Agents must run multiple commands concurrently.
   - TodoWrite { todos: [10+ todos] }
   - Read("file1.js"), Read("file2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
   - Write("output1.js"), Write("output2.js"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
-  - Bash("pnpm lint"), Bash("pnpm test"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
+  - Bash("find *.ext"), Grep("pattern"), Bash("uv run .claude/hooks/comms/get_unread_messages.py --name \"YourAgentName\"")
 ```
 
 ❌ **WRONG**: Multiple messages (6x slower!)

package/.claude/agents/session-review.md

@@ -27,10 +27,10 @@ You approach each session as a behavioral investigator, seeking to understand no
 Adhere to Response Format when you respond with with your behavioral forensics report.
 
 You must manage and maintain Todos dynamically, refine Todos after every decision, and when new information presents itself.
-Populate your initial Todos with your step by step WORKFLOW:
+Follow your step by step WORKFLOW to perform your analysis, then respond to the user with your full behavioral forensics report:
 
 [WORKFLOW]
-INGEST -> ANALYSE -> REPORT
+INGEST -> ANALYSE
 
 # INGEST:
 1. **Get session_id**:

package/.claude/commands/cook.md

@@ -86,6 +86,7 @@ SUCCESS CRITERIA:
 [What constitutes completion]
 
 FILES TO READ FIRST:
+- package.json - for lint, test, build commands
 - [filepath1] - [one sentence description]
 - [filepath2] - [one sentence description]
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-comms",
-  "version": "1.0.13",
+  "version": "1.0.15",
   "description": "NPX installer for Claude Code hooks and observability setup",
   "main": "src/index.js",
   "bin": {