- Enable forgetful, context7, context-hub plugins in settings.json
- Add forgetful MCP server config to .mcp.json (HTTP transport)
- Document Forgetful tools and usage patterns in CLAUDE.md
- Add Forgetful to memory system docs in copilot-instructions.md
- Add complete setup guide for Linux/Windows in CONTRIBUTING.md

Note: HTTP transport required due to FastMCP banner corruption
(upstream issue: ScottRBK/forgetful#19)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

- Install uv (Python package manager) for uvx command
- Start Forgetful MCP server in HTTP mode on port 8020
- Add health check verification in test summary
- Wait up to 30s for server startup

Enables AI agents in Copilot workspace to use semantic memory.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

QA verification artifact for spec layer traceability implementation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Implement Claude Code hooks to enforce ADR-007 Memory-First Architecture
at runtime. Hooks inject context into Claude's session to ensure memory
retrieval precedes reasoning.

## Hooks
- Invoke-SessionStartMemoryFirst.ps1: Injects Phase 1/2 blocking gate
  requirements at session start (Serena init + context retrieval)
- Invoke-UserPromptMemoryCheck.ps1: Detects planning/implementation
  keywords and reminds about memory-first workflow

## Configuration
- .claude/settings.json: Registers hooks for SessionStart and
  UserPromptSubmit events using pwsh cross-platform execution

## Tests
- 34 Pester tests covering both hooks
- Keyword detection, case insensitivity, JSON parsing, output content

Addresses Issue #729 (E1: Claude Code Hooks)
Per ADR-005: PowerShell-only with Verb-Noun naming conventions

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Multi-agent ADR review artifacts for ADR-007 Memory-First Architecture:

## Analysis
- ADR-007-enforcement-gap-analysis.md: Identifies 5 gaps, tracks E1/E3
  as resolved, E2/E4/E5 pending (Issue #729)
- ADR-007-related-work-research.md: Phase 0 research on related issues

## Critique (6-agent debate)
- ADR-007-debate-log.md: Full debate protocol, 6/6 consensus achieved
- ADR-007-memory-first-architecture-critique.md: Critic agent review
- ADR-007-analyst-independent-review.md: Analyst agent findings

## Serena Memories
- adr-007-augmentation-research.md: Forgetful/BMAD/Zettelkasten research
- memory-architecture-serena-primary.md: Serena as canonical layer
- skill-usage-mandatory.md: Fills gap referenced in CLAUDE.md (E3)

Completes ADR-007 review per adr-review skill protocol.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

## ADR-007 Updates (per 6-agent review)
- Added Confirmation section with verification methods
- Added Implementation Status section
- Added Security Considerations (CWE references)
- Added Tool Selection clarification (Serena canonical)
- Added Relationship to Issue #167 section
- Qualified SWE-Bench claim per analyst feedback

## Context-Hub Commands
- Minor updates to memory commands from plugin integration
- Added context-retrieval agent configuration

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Add Test-MemoryEvidence function to Validate-Session.ps1 that:
- Finds memory-index row in Session Start checklist
- Detects placeholder evidence (empty, template text, brackets)
- Extracts memory names using kebab-case regex pattern
- Verifies each memory exists in .serena/memories/

Error codes: E_MEMORY_EVIDENCE_INVALID, E_MEMORY_NOT_FOUND

Includes 12 Pester tests covering valid evidence, placeholder
detection, invalid names, and edge cases.

Closes trust gap where agents could self-report memory retrieval
without actually doing it.

Related: ADR-007, Issue #729

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Add lightweight memory evidence check (lines 842-890) that:
- Finds memory-index row in staged session log
- Extracts Evidence column content
- Warns on placeholder patterns (empty, template text, brackets)
- Validates kebab-case memory name format

Non-blocking warning only - E2 validation provides full enforcement.

Related: ADR-007, Issue #729

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Updates to ADR-007 Memory-First Architecture:

- Fix memory workflow to Serena-first (was incorrectly Forgetful-first)
  Read → Augment → Persist → Commit

- Add Fallback Behavior section documenting graceful degradation:
  - Forgetful not running: Use Serena memory-index
  - Forgetful timeout: Proceed with loaded memories
  - Fresh environment: Full Serena workflow

- Document MUST NOT rules for fallback scenarios
- Add evidence format for Forgetful-unavailable sessions

Addresses P1 debate items: workflow priority, undefined fallback.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Mark E2 and E4 as complete in gap analysis:
- E2: Enhanced Session Validation (Validate-Session.ps1)
- E4: Pre-commit Memory Evidence Check (.githooks/pre-commit)

Update implementation priority table with completion status.
Update success criteria checklist (4/5 complete).

Remaining: E5 Forgetful Verification (P2)

Related: Issue #729

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Add comprehensive issue resolution handling:

## P0/P1 Resolution
- P0 must be fully addressed (blocking)
- P1 must be addressed OR deferred with justification + backlog issue

## P1 Deferral Requirements
- Documented justification in ADR/debate log
- GitHub issue with priority:P1, backlog, adr-followup labels
- Linked to related issues/ADRs for surfacing
- Keywords in title matching memory-index patterns

## Surfacing Mechanism (for amnesiac agents)
- GitHub issue linking (surfaces when working on linked items)
- Phase 0 search (searches label:adr-followup)
- Memory-index keywords (surfaces during Session Start)

## P2 Backlog
- Filed as GitHub issues with backlog, adr-followup labels
- Documented in debate log

Includes practical example, issue templates, and post-creation steps.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

- README.md: Comprehensive setup guide for humans and AI agents
- Install-ForgetfulLinux.ps1: systemd user service installation
- Install-ForgetfulWindows.ps1: Windows scheduled task installation
- Test-ForgetfulHealth.ps1: Health check with TCP and service status

Uses uvx for always-up-to-date package execution. HTTP transport on
port 8020 to work around upstream stdio bug (FastMCP banner corruption).

Related: ADR-007 Memory-First Architecture

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Hook now checks if Forgetful MCP is available via TCP port check and
provides appropriate guidance:

- When available: includes optional Forgetful step in context retrieval
- When unavailable: shows fallback guidance and installation commands

Uses TCP connection check instead of full MCP protocol (which requires
session initialization) for quick, reliable detection.

Related: ADR-007 Memory-First Architecture

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

- CLAUDE.md: Add health check command and setup reference
- copilot-instructions.md: Add setup reference and health check

Points to scripts/forgetful/README.md for installation details.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

- Convert bash to PowerShell for consistency (ADR-005)
- Use TCP port check instead of invalid /health endpoint
- MCP HTTP transport requires session initialization for full protocol
- Reference scripts/forgetful/README.md for local setup documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

## Root Causes Fixed
1. Memory file naming violation (ADR-017): Remove duplicate skill-usage-mandatory.md
   - File used 'skill-' prefix which violates ADR-017 naming convention
   - usage-mandatory.md already exists with same content
   - Updated CLAUDE.md references to use 'usage-mandatory'

2. ErrorActionPreference style violation (gemini-code-assist feedback)
   - Changed from 'SilentlyContinue' to 'Stop' per style guide
   - Added 'finally' block for proper resource cleanup

3. systemd ExecStart paths (gemini-code-assist feedback)
   - Changed /home/$USER/ to %h/ specifier for portability
   - Applied in both CONTRIBUTING.md and scripts/forgetful/README.md

4. Fixed corrupted PowerShell comment terminator
   - '# >' was corrupted to '# >' (with space) by linting

## Not Fixed (pre-existing CI issue)
- Generate-Skills.Tests.ps1 failure: PSGallery not accessible
  (powershell-yaml module install fails)
  User has added PSGallery URLs to firewall allowlist

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Enhances UserPromptSubmit hook to detect PR creation requests and inject
pre-PR validation checklist. This prevents CI failures by reminding the
agent to:

1. Run local Pester tests
2. Validate PowerShell script syntax
3. Check memory file naming (ADR-017)
4. Read validation-pre-pr-checklist memory
5. Avoid running markdownlint on .ps1 files

Triggered by keywords: "create pr", "open pull request", "gh pr create"

Adds 8 new Pester tests for PR detection functionality.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Enhances the UserPromptMemoryCheck hook to detect GitHub CLI commands
and remind users to check for existing skills before using raw gh CLI.

Detected commands:
- gh pr create/list/view/merge/close/checks/review/comment/diff/ready/status
- gh issue create/list/view/close/comment/edit
- gh api (including GraphQL)
- gh run/workflow

Test coverage:
- 75 tests covering all detection patterns
- Case insensitivity verification
- Multiple trigger combination tests
- Non-triggering pattern tests

Memory:
- Added validation-pre-pr-checklist memory with CI failure learnings

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Fixes identified by multi-agent review (code-reviewer, silent-failure-hunter,
pr-test-analyzer, comment-analyzer):

## Critical Fixes
- Add exception logging to silent catch block (Invoke-SessionStartMemoryFirst.ps1:45-47)
- Replace TcpClient.Close() with Dispose() for proper cleanup
- Fix SilentlyContinue to ErrorAction Stop (Invoke-UserPromptMemoryCheck.ps1:50)
- Fix .sh references to .ps1 in ADR-007-enforcement-gap-analysis.md

## Naming Consistency (ADR-017 Compliance)
- Update SESSION-PROTOCOL.md to use usage-mandatory (not skill-usage-mandatory)
- Update PROJECT-CONSTRAINTS.md to use usage-mandatory
- Update gap analysis document to reference correct file path
- Update code-style-conventions.md with correct path

## Governance
- Add historical-reference-protocol.md for artifact traceability

All 84 Pester tests pass.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

- Add $LASTEXITCODE checks after systemctl commands in Linux installer
- Wrap Register-ScheduledTask in try/catch in Windows installer
- Exit with code 1 on failure with descriptive error messages

Addresses PR #730 review findings (P1-1, P1-2)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Replace incorrect REST /health endpoint with correct JSON-RPC POST
to /mcp endpoint using tools/list method. Matches actual MCP protocol
used by installation scripts.

Addresses PR #730 review findings (P1-3)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Add finally block with Dispose() for TcpClient to ensure cleanup
on all code paths (success, timeout, exception). Follows .NET
IDisposable best practices.

Addresses PR #730 review findings (P2-1)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Handle edge case where TCP connection attempt completes but
$tcpClient.Connected is false. Sets explicit "connection timeout"
message for better debugging.

Addresses PR #730 review findings (P2-2)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Rename skill-usage-mandatory to usage-mandatory across 7 files.
ADR-017 removed skill- prefix from memory naming convention.

Files updated:
- AGENTS.md (4 refs)
- src/claude/AGENTS.md (2 refs)
- .claude/skills/AGENTS.md (3 refs)
- .claude/agents/AGENTS.md (2 refs)
- .claude/skills/github/references/api-reference.md (1 ref)
- .claude/skills/session-log-fixer/references/template-sections.md (2 refs)
- docs/technical-guardrails.md (1 ref)

Addresses PR #730 review findings (P3-2)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Change ADR cross-reference example from real ADR-005 reference to
placeholder notation (ADR-NNN, YYYY-MM-DD, Issue #NNN) to clarify
this is a format template, not documenting a real relationship.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Add missing dates to PR, issue, and commit references in analysis
documents per historical-reference-protocol.md requirements.

Files fixed:
- 003-quality-gate-comment-caching-rca.md: 5 references
- 281-similar-pr-detection-review.md: 3 references

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>