330 tagged codex, measured the same way as everything else here.
Browse within: claude-code-plugin 128codex-cli 92agent-memory 77codex-plugin 74ai-coding 63local-first 40gemini-cli 38gemini 31coding-agent 29coding-agents 28opencode 27agent-orchestration 26hooks 26knowledge-graph 25
ecodelearn/template-claude-code-ts
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Edit and Write tool calls, executing auto-format.sh via bash (2 commands). From ecodelearn/template-claude-code-ts.
Hook Claude Code
One of 2 in settings.json
Runs when a session starts, executing gh-setup.sh. From LangcliTeam/Langpad.
Hook
One of 2 in hooks.json
Runs when you submit a prompt, before the agent sees it, executing route-remote-prompt.cjs via node. From Liyuchen0118/RunBeacon.
Hook
One of 2 in hooks.json
Runs before the agent uses a tool for ^mcp__(?:runbeacon, remote[-_]job[-_]monitor)__job_start$ and ^Bash$ tool calls, executing inject-job-trace.cjs and route-ssh.cjs via node (2 commands). From Liyuchen0118/RunBeacon.
Hook
Runs when a session starts on startup and resume, executing session-start-turncue.mjs via node. From xuhuawork/turncue.
Hook
One of 11 in hooks.json
Runs when a session starts, executing record-hook.mjs via node. From jiangkoumo/agenttape.
Hook
One of 11 in hooks.json
Runs before the agent uses a tool, executing record-hook.mjs via node. From jiangkoumo/agenttape.
Hook
One of 11 in hooks.json
Runs when the agent finishes a response, executing record-hook.mjs via node. From jiangkoumo/agenttape.
mp-juns/universal-research-mcp
Hook
Runs when a session starts on ^(startup, resume, clear and compact)$, executing session_start.py via python3. From mp-juns/universal-research-mcp.
Hook
One of 8 in hooks.json
Runs when a session starts on startup, resume, clear and compact, executing room.py. From TallyUp-Engineering/chat-room.
Hook
One of 8 in hooks.json
Runs when you submit a prompt, before the agent sees it, executing room.py. From TallyUp-Engineering/chat-room.
Hook
One of 8 in hooks.json
Runs before the agent uses a tool for Write, Edit, NotebookEdit and Bash tool calls, executing room.py. From TallyUp-Engineering/chat-room.
Hook
Runs when you submit a prompt, before the agent sees it, executing context.mjs via node. From Johnnybyzhang/post-plan.
ar36planet/claude-codex-bridge-public
Hook Claude Code
One of 2 in settings.json
Runs when the agent finishes a response, executing inbox.mjs via node with --as. From ar36planet/claude-codex-bridge-public.
Hook
Runs when a session starts, executing session-start.cjs via node. From devcodex-labs/devcodex.
Hook
Runs when you submit a prompt, before the agent sees it, executing devcodex-workspace.cjs via node. From devcodex-labs/devcodex.
Hook
Runs before the agent uses a tool, executing devcodex-workspace.cjs via node. From devcodex-labs/devcodex.
Hook Claude Code
Runs when a session starts on startup, resume and compact, executing startup-context-loader.sh, resume-context-loader.sh and postcompact-restore.py (3 commands). From flonat/flonat-research.
Hook Claude Code
Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing protect-source-files.sh and block-destructive-git.sh (2 commands). From flonat/flonat-research.
Hook Claude Code
Runs when the agent finishes a response, executing promise-checker.sh. From flonat/flonat-research.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing check-version-format.sh via sh with --show-toplevel. From fitlab-ai/agent-infra.
Hook Claude Code
Runs when a subagent starts for agent-infra-lifecycle-(executor and reviewer) tool calls, executing lifecycle-delegation.js via node with --show-toplevel and --client. From fitlab-ai/agent-infra.
Hook Claude Code
Runs when a subagent finishes for agent-infra-lifecycle-(executor and reviewer) tool calls, executing lifecycle-delegation.js via node with --show-toplevel and --client. From fitlab-ai/agent-infra.
Hook Claude Code
Runs before the agent uses a tool for Bash, Write, Edit, mcp__coding-os__cos_task_create, mcp__coding-os__cos_task_move, mcp__coding-os__cos_work_log_append, Write, Edit, MultiEdit, Read and Edit tool calls, executing block-secrets.sh, block-dangerous-commands.sh, block-uv-heredoc.sh, branch-guard.sh…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: