| name | logseq-review-workflow |
| description | Review Logseq code changes, PRs, patches, commit ranges, or implementation plans through one main-agent orchestration workflow that routes read-only subagents across independent review passes, then deduplicates, validates, and reports findings for the web app, desktop app, and Logseq CLI. |
Logseq Review Workflow
Core principle
The main agent drives the review. It identifies scope, loads routing rules, launches independent read-only subagents for each review pass, collects candidate findings, validates the actionable ones, deduplicates overlap, and writes the final conclusion.
Each pass subagent only collects issues. It must not edit files, stage changes, commit, push, or rewrite code. It returns candidate findings, evidence, checks already run, and unresolved questions to the main agent.
Review every pass through three layers:
- Repository-wide rules — always apply shared review behavior from
rules/common.md.
- Library/runtime/tooling rules — apply when the diff uses or changes a specific library, language/runtime surface, or tooling dependency.
- Logseq module rules — apply when the diff touches a specific product/runtime area.
Use the routing tables below to load the most specific matching rule files.
Prefer concrete findings backed by code paths, invariants, tests, or runtime behavior. Do not list speculative issues unless you can explain the failure mode and affected scenario.
Every actionable finding with an executable Logseq behavior path must be validated through at least one real Logseq interaction path before it is included in the final review. Use logseq-repl, logseq-cli, chrome, or computer-use depending on the touched surface. For implementation plans, docs-only changes, static configuration errors, missing migrations, schema/protocol invariant breaks, or other findings without an executable behavior path, validate through code paths, invariant evidence, tests, build/lint output, or documented contracts and state why runtime interaction does not apply.
