Agent skill
ln-315-review-merge-worker
Use when an evaluation run must merge research, findings, documentation, and repair outputs into one verified result.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/ln-315-review-merge-worker
SKILL.md
Paths: File paths (
shared/,references/,../ln-*) are relative to skills repo root.
Type: L3 Worker Category: 3XX Planning
Review Merge Worker
Mandatory Read
MANDATORY READ: Load shared/references/evaluation_worker_runtime_contract.md, shared/references/evaluation_summary_contract.md
MANDATORY READ: Load shared/references/agent_delegation_pattern.md (Critical Verification + Background Execution sections)
Purpose
- merge read-only evidence lanes after their join barrier
- deduplicate overlap against prior review history
- produce one verified aggregate result for the coordinator
Wait/Patience Protocol
Codex typically takes 10-20 minutes. Do NOT skip or declare an agent failed based on elapsed time. Only the Liveness Protocol in agent_delegation_pattern.md determines failure.
Runtime
Runtime family:
evaluation-worker-runtime
Required manifest fields:
identifierphase_ordersummary_kind=review-mergeoperation=merge
Recommended phase_order:
PHASE_0_CONFIGPHASE_1_LOAD_WORKER_RESULTSPHASE_2_DEDUPLICATE_AND_VERIFYPHASE_3_WRITE_SUMMARYPHASE_4_SELF_CHECK
Workflow
Phase 1: Load Worker Results
- Load all input worker summaries (ln-311, ln-312, ln-313, ln-314).
- Load agent findings from external agents (Codex, Gemini).
- Load
.hex-skills/agent-review/review_history.mdfor prior review entries.
Phase 2: Deduplicate and Verify
- Deduplicate current findings against:
- own analysis
- worker findings
- agent findings
- prior review history
- For each agent suggestion: independently verify per
agent_delegation_pattern.mdCritical Verification criteria. - Mark each suggestion
AGREEorREJECT. - Architecture Gate: Before accepting any AGREE'd suggestion, verify: "Does this implement the correct architecture directly, without backward compatibility shims or legacy workarounds?" If a suggestion introduces unnecessary compat layers, convert AGREE to REJECT.
- Reject unsupported findings.
Phase 3: Write Summary
Emit summary_kind=review-merge.
Payload must include:
worker=ln-315statusoperation=mergewarnings
Prefer these fields when available:
merge_summary.accepted_countmerge_summary.rejected_countmerge_summary.dedup_removedmerge_summary.architecture_gate_rejections
Save updated review summary to .hex-skills/agent-review/review_history.md.
Phase 4: Self-Check
- Verify deduplication completed.
- Verify architecture gate applied to all AGREE'd suggestions.
- Record
pass=trueonly after summary write.
Definition of Done
- Input worker summaries loaded
- Agent results loaded and verified per Critical Verification
- Duplicates removed (against findings + review history)
- Architecture Gate applied to all accepted suggestions
- Review summary saved to
review_history.md -
review-mergesummary written - Self-check passed
Version: 1.0.0 Last Updated: 2026-04-10
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?