- Add branchName() and worktreePath() helpers for consistent path generation
- Add msToTime() for epoch ms to Time conversion (8 occurrences consolidated)
- Add validateTaskId() for CLI input validation (prevents path traversal)
- Add optString/optInt64 helpers for nullable DB values
- Add withTransaction template for automatic rollback on error
Closes: skills-lzh2, skills-3d9o, skills-5x2o, skills-qiq0, skills-73yu, skills-vuj2
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- genOid: use std/sysrand for cryptographic randomness instead of rand()
- HeartbeatThread: change from ptr with manual alloc/dealloc to ref object
- Add error handling for DB open in heartbeat thread
- Remove unused globalChannel and times import
Closes: skills-0wk, skills-bk7x, skills-69sz, skills-ib9u, skills-kvdl, skills-n6zf
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Covers: review-gate Stop hook fixes, circuit breaker, research on
OpenHands/Gastown/JWZ patterns, epic creation, phased approach
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Track block attempts per session in .attempts file
- After 3 attempts (configurable via REVIEW_MAX_ATTEMPTS), trip breaker
- Circuit breaker allows exit with warning instead of crashing
- Clear attempts on approve or when breaker trips
- Add 3 new tests for circuit breaker behavior (46 total)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When Claude continues after a Stop hook block, the next Stop hook
invocation has stop_hook_active: true. Detect this and allow exit
to break the loop and prevent stack overflow crash.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change exit code to 2 (Claude Code blocking signal)
- Output JSON to stderr with decision: block and reason fields
- Add integration test harness for live Claude testing
- Update unit tests for new JSON output format
- Add hooks.json example for Stop hook
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Tests cover:
- All CLI commands (check, enable, approve, reject, status, list, clean)
- Exit codes (0 for allow, 1 for block)
- State file creation and JSON structure
- Session ID auto-detection from env vars
- Multiple issues in reject
- Workflow reset (re-enable after approve)
- Error handling
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- CLI tool with check/enable/approve/reject/status commands
- Stop hook integration for Claude Code blocking
- Adversarial reviewer prompt template
- Dual-publish structure (SKILL.md + .claude-plugin)
- Session ID auto-detection from env vars or git state
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Comprehensive comparison of Claude Code, Gemini CLI, OpenCode, and Codex:
- Hooks/lifecycle events (Claude/Gemini best, OpenCode most comprehensive)
- Subagent spawning (MCP is universal bridge)
- File access (Gemini has path restrictions - skills-bo8)
- Sandboxing (Codex has OS-level, others approval-based)
- State persistence (need external store for cross-agent)
Key finding: Orchestrator pattern works across all agents.
Stop hooks only in Claude/Gemini - others need protocol-based gates.
Closes: skills-fqu
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
alice is for reviewing AGENT work in unattended/autonomous contexts,
not code review. Key use cases:
- Autonomous runs on ops-jrz1
- CI/CD pipelines with agents
- High-stakes changes without human oversight
Added hybrid approach recommendation: use alice concepts (Stop hook,
adversarial methodology) with our infrastructure (beads, orch).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Comprehensive analysis of emes idle/alice plugin:
- Hook chain (6 hooks, Stop is key blocker)
- State management via jwz (topic-based messaging)
- alice agent (read-only Opus reviewer)
- Circuit breakers against infinite loops
Conclusion: alice pattern is overkill for code-review (we ARE the
reviewer). More useful: "review reminder" hook that checks if
code-review was run before exit on significant changes.
Closes: skills-9jk
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Local (skills, dotfiles): beads + our dual-publish
Remote (ops-jrz1 VPS): tissue + emes ecosystem
They coexist by environment, not replacing each other.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Compares three approaches:
- Our system: cross-agent, Nix, lenses
- Claude plugins: official, hooks, marketplace
- emes: mechanical enforcement, tissue, idle, jwz
Living document for iterating on architecture.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Captures the decision to maintain both:
- Nix deployment (cross-agent: Gemini, OpenCode)
- Claude plugin system (hooks, marketplace)
Documents trade-offs, consequences, and mitigations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
