agentlogbooks/logbooks

agentlogbooks/logbooks

Plugin Claude Code

Plugin marketplace listing 4 plugins: logbook-creator, deep-code-review, ideation, mutation-testing.

agentlogbooks/logbooks

Plugin Claude Code

A collection of agent skills backed by logbooks — structured, queryable, session-persistent working surfaces. Examples: design and create a logbook, run a multi-angle code review with per-PR findings logbook.

agentlogbooks/logbooks

Plugin Claude Code

Hotspot-first deep code review: change map → risky hotspot selection → per-hotspot lens subagents → skeptic pass → comment budget. Surfaces at most 5 high-signal findings or questions per run.

agentlogbooks/logbooks

Plugin Claude Code

Idea-centric brainstorming built on a persistent per-topic idea logbook. Operators (generate, transform, evaluate, validate, decide) read and write ideas across sessions; thin planner picks operators from a library and composes them into playbooks. Supersedes deep-ideation.

agentlogbooks/logbooks

Plugin Claude Code

Design and create a logbook — a shared, queryable, schema-stable working surface for agents and humans to append, annotate, and query across sessions.

agentlogbooks/logbooks

Plugin Claude Code

Validates test quality beyond coverage: uses Claude subagents to generate intelligent mutations for source code, executes them via the project's native test runner, extracts survived mutants, generates mutation-todos.md with rationale, and persists run history to a SQLite logbook.