Reviews an existing codebase for structural friction, unclear ownership, leaky or shallow interfaces, excessive coupling, misplaced state, poor testability, and risky dependency direction, then prioritizes evidence-backed improvement candidates. Use for architecture audits, modularization, modernization, or recurring cross-cutting change pain. Not for designing one new interface, simplifying a local function, or fixing a reproduced bug.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Find structural changes that reduce the cost and risk of likely future work. Do not produce a generic best-practices checklist.
Use codebase-orientation first when ownership and execution paths are not
known. Focus on the user-named subsystem or on evidence-backed hotspots from
history, incidents, change coupling, and test failures. Read relevant ADRs and
domain vocabulary before proposing alternatives.
Look for:
Apply the deletion test: if removing a module only moves its complexity into every caller, it may be earning its place; if complexity disappears, it may be ceremony. Use candidate-report.md to compare current and proposed ownership.
Rank candidates by observed friction, expected locality/leverage, migration risk, reversibility, and relevance to upcoming work. Include a smallest useful change and explicit non-goals. Mark speculative ideas as speculative.
Hand an approved candidate to solution-design and
implementation-planning; use code-simplification when no architectural
boundary changes.
The report ties each candidate to repository evidence, shows current and proposed ownership, respects existing decisions or explicitly challenges them, and recommends a bounded first move without implementing an unapproved redesign.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Designs and runs reproducible evaluations for AI agents, prompts, tools, skills, and model-backed workflows using realistic datasets, isolated baselines, objective assertions, rubric grading, trajectory analysis, cost/latency tracking, and regression comparison. Use when measuring agent quality, optimizing skill triggering, comparing prompts or models, or gating an AI feature release. Not for ordinary deterministic unit tests.
日本語の概要は準備中です。原文の説明を表示しています。
Designs or reviews HTTP, REST, GraphQL, RPC, CLI, webhook, event, and service interfaces with explicit inputs, outputs, errors, compatibility, idempotency, pagination, authentication, versioning, and observability. Use when introducing or changing an API or cross-component contract. Not for internal implementation details with no boundary or for debugging one API failure; use root-cause-debugging there.
日本語の概要は準備中です。原文の説明を表示しています。
Validates a running application, CLI, API, service, or generated artifact as a user or operator against a prewritten observable behavior contract while remaining source-blind. Use for acceptance checks, runtime proof, anti-fake probes, release smoke tests, or an independent companion to code review. Not for source-quality findings, root-cause diagnosis, or visual design judgment outside the contract.
日本語の概要は準備中です。原文の説明を表示しています。
Closes a completed development branch by checking the final diff and proof, presenting merge, pull-request, keep, or discard options, and cleaning up only after the user or repository workflow chooses a path. Use when feature work is complete and the branch must be integrated or retired. Not for claiming a feature is complete before verification.
日本語の概要は準備中です。原文の説明を表示しています。
Tests a real web user flow with a browser by asserting semantic behavior, network and loading states, keyboard access, responsive layouts, and stable visual evidence. Use for browser bugs, end-to-end UI behavior, responsive or accessibility checks, and screenshot baselines. Not for static source review without a browser or for backend-only tests.
日本語の概要は準備中です。原文の説明を表示しています。
Simplifies recently changed or explicitly scoped code while preserving observable behavior, error semantics, side effects, ordering, and public contracts. Use for readability cleanup, dead-code removal, reducing nesting, eliminating redundant wrappers, or making an implementation easier to maintain. Not for architecture redesign, new behavior, speculative cleanup, or a refactor without an adequate safety net.
日本語の概要は準備中です。原文の説明を表示しています。