code-review · git:20260904.fc73049 · 2026-09-04 · sha256 32aa2596cc3c6cf3

code-review git:20260904.fc73049A

Immutable. This exact content never changes and is served at /api/v1/blob/32aa2596cc3c6cf3.

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_y6ll5m4iw6huwr3g/32aa2596cc3c6cf3da67c78ed94a11a51c75c5bc4f9a9b814bfb1ec31cc69d60.json

Then /plugin install code-review@markdownregistry-y6ll5m4iw6huwr3g in Claude Code. It installs this exact version, the one graded A here, pinned to the commit it was graded at, and leaves it there.

---
name: code-review
description: Review Langfuse code changes for correctness, regressions, and best practices.
---

# Code Review

Use this skill when the task is to review code changes rather than implement a
feature.

## Start Here

- Read [`references/review-checklist.md`](references/review-checklist.md) for
  the repo's canonical review rules.
- Read root [`AGENTS.md`](../../../AGENTS.md) and the nearest package
  `AGENTS.md` for the files under review.
- If the review touches ClickHouse, also use the shared
  `clickhouse-best-practices` skill.
- If the review touches backend code, also use the shared
  `backend-dev-guidelines` skill where relevant.
- If the change accepts a user-supplied URL, adds outbound HTTP, introduces a
  new integration, touches secrets, RBAC, redirect handling, product
  analytics, browser monitoring, or session replay, also use the shared
  [`security-review`](../security-review/SKILL.md) skill. Run its
  [`references/checklist.md`](../security-review/references/checklist.md)
  before signoff.

## Review Priorities

Focus on:

- correctness bugs
- behavioral regressions
- security and tenant-isolation risks
- performance issues with real impact
- missing or weak tests for risky changes
- Before calling coverage missing, identify the unique regression each proposed
  test catches. Do not ask for one whose only assertion would restate the diff —
  a spacing value, a label — because it costs a file and proves nothing. Prefer merging into the closest existing suite. Flag repeated
  tests of the same predicate across layers unless each proves a distinct
  transport, projection, or execution boundary.

## Output Expectations

- Findings first, ordered by severity
- File and line references for each finding
- Short summary only after findings
- If no findings, say so explicitly and mention any residual risk or coverage gaps

## Scope Guidance

Use `references/review-checklist.md` for Langfuse-specific checks such as:

- ClickHouse and Postgres migration expectations
- project-scoped tenant isolation checks
- API/Fern consistency
- banner-offset UI positioning
- environment variable access patterns

Do not duplicate those rules in ad hoc prompts or tool-specific command files.