codex-reviewer
claudecodexOpt-in stand-in for Codex's GitHub code review when it is unavailable: a read-only agent with Codex's open-source review rubric (Claude Code only).
1 agent
Core of agent-loadout: Serena and codebase-memory MCP servers, tool hooks, and skills for onboarding, docs, changing your loadout setup, plan execution advice and tool-use reports.
Plugin loadout from marketplace agent-loadout in jonasyr/agent-loadout. Commands read from the repo's manifest — 8 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
configureAnswer any question about loadout (agent-loadout) from its docs, and make changes to the user's loadout setup through the `loadout` CLI - preferences, plugins, MCP servers, own tools, agents (Claude Code, Codex), project profiles, checks, updates, restore. Use whenever the user asks how loadout work
docs-auditFull, expensive audit of all docs and memories in a repo — verifies every claim against the current code, asks about anything unclear, and rewrites everything into the loadout docs structure (docs/ as single source of truth). Resumable. Use when docs or memories may be stale, wrong or duplicated.
docs-syncCheap end-of-feature documentation pass — find which doc layers (docs/, AGENTS.md, Serena memories, README) the current change affects and update only those, then verify links. Use after finishing a feature or before merging.
execution-advisorRecommend how to execute an implementation plan — Inline, subagent-driven (SDD) or a Hybrid with a per-task table (mode, model tier, review) — from a rubric instead of defaulting to subagents. Use right after a plan is written, when a hook asks for it, or when the user asks "SDD or inline?" / how to
onboardSet up a repository for agent work — new/empty repos get a guided project definition (purpose, stack, structure, first ADR); existing repos get an accurate AGENTS.md, Serena memories and a codebase-memory index. Use after `loadout init`, or when a repo has no AGENTS.md.
releaseCut a loadout release with good notes - draft the Keep a Changelog section from the merged PRs, rewrite it for people who use loadout, and release only after the person says yes to it. Use when the user asks to release, cut a release, publish vX.Y.Z or write release notes.
usageReport how often the agents used Serena, codebase-memory, Context7 and Microsoft Learn versus grep and the shell, from `loadout usage` (counts only), and whether a change (Serena's reminder, loadout's setup) helped, as before/after. Use when the user asks whether the tools or hints are used, whether
serenaruns: serena start-mcp-server --context=claude-code --project-from-cwd
codebase-memory-mcpruns: codebase-memory-mcp
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/mcp_guard.py" serena serena-hooks activate --client=claude-code
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" loadout hook-session-start --agent claude
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/reload_check.py"
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/cbm_project.py" session-start --agent claude
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/mcp_guard.py" serena serena-hooks cleanup --client=claude-code
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" rtk hook claude
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/mcp_guard.py" serena serena-hooks auto-approve --client=claude-code
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/mcp_guard.py" serena serena-hooks remind --client=claude-code
"${CLAUDE_PLUGIN_ROOT}/hooks/tool_hint.sh"
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/advisor.py" record
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/refresh.py" --agent claude
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/advisor.py" stop
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/reload_check.py"
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/refresh.py" --agent claude
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/refresh.py" --agent claude
"${CLAUDE_PLUGIN_ROOT}/hooks/subagent-context.sh" claude
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" --soft --python "${CLAUDE_PLUGIN_ROOT}/hooks/cbm_project.py" subagent-start --agent claude
Opt-in stand-in for Codex's GitHub code review when it is unavailable: a read-only agent with Codex's open-source review rubric (Claude Code only).
1 agent
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.