agent-skills hooks

61 tagged agent-skills, measured the same way as everything else here.

Browse within: claude-code-plugin 137cursor 65agentic-ai 56ai-coding 46agents 45agentic-workflow 39agentic-coding 36skills 35claude-code-skills 31codex-cli 31cli 29Autonomous Agents 25codex-plugin 25agent-memory 22

SessionStart

01

brycewang-stanford/Auto-Empirical-Research-Skills

Hook Claude Code

One of 3 in hooks.json

Runs when a session starts on compact and resume, executing setup-project-dirs.sh and post-compact-restore.py via bash (2 commands). From brycewang-stanford/Auto-Empirical-Research-Skills.

not rated 4.6k +90 yesterday A tokens not measured

PostToolUse

02

alibaba/skill-up

Hook Claude Code ✓ vendor

One of 4 in hooks.json

Runs after a tool call finishes for ^mcp__skill_up_observer__(mark_skill_invocation, attach_skill_evidence and record_skill_feedback)$ tool calls, executing observer.py via python3. From alibaba/skill-up.

not rated 1.2k +51 2d ago A tokens not measured original Apache-2.0

UserPromptSubmit

03

EverMind-AI/SkillCorpus

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing hook.mjs via node. From EverMind-AI/SkillCorpus.

not rated 686 +2 yesterday A tokens not measured original Apache-2.0

SessionStart

04

jiabaobei/skills-constitution

Hook Claude Code

One of 2 in hooks.json

Runs when a session starts on startup, resume, clear and compact, executing session-start.sh via bash. From jiabaobei/skills-constitution.

not rated 234 +2 13d ago A tokens not measured original MIT

PostToolUse

05

serradura/okf

Hook Claude Code

One of 5 in settings.json

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, running "$CLAUDE_PROJECT_DIR"/.claude/hooks/run post-edit. From serradura/okf.

not rated 179 +1 1mo ago A tokens not measured copy · 44% Apache-2.0

SessionStart

06

k-kolomeitsev/data-structure-protocol

Hook Claude Code

One of 5 in settings.json

Runs when a session starts, executing dsp-session-start.sh. From k-kolomeitsev/data-structure-protocol.

not rated 68 2mo ago A tokens not measured original Apache-2.0

PostToolUse

07

aleclindz/seo-skill-bench

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From aleclindz/seo-skill-bench.

not rated 51 yesterday A tokens not measured original MIT

PreToolUse

08

buildinternet/uploads

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From buildinternet/uploads.

not rated 18 today A tokens not measured original Apache-2.0

SessionStart

09

frabcd/codex-ai-game-studio

Hook Claude Code

One of 9 in hooks.json

Runs when a session starts on startup, resume, clear and compact, executing hook_dispatch.py via python3. From frabcd/codex-ai-game-studio.

not rated 17 +1 4d ago A tokens not measured original MIT

PreToolUse

10

StringNLPLAB/FlexSQL

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for mcp__snowflake-tools__(query_database, python_interpreter) and Write tool calls, executing require_writing.py and require_revision.py via python3 (2 commands). From StringNLPLAB/FlexSQL.

not rated 11 1mo ago A tokens not measured

BeforeTool

11

itallstartedwithaidea/google-ads-gemini-extension

Hook Claude Code

One of 2 in hooks.json

Runs on the BeforeTool event for run_gaql tool calls, executing validate-gaql.js via node. From itallstartedwithaidea/google-ads-gemini-extension.

not rated 9 3mo ago A tokens not measured original MIT

SessionStart

12

jscraik/Agent-Skills

Hook Claude Code

Runs when a session starts, executing session_start_contract.py via python3. From jscraik/Agent-Skills.

not rated 9 4d ago A tokens not measured original Apache-2.0

PreToolUse

13

dmytri/shipshape

Hook Claude Code

One of 4 in hooks.json

Runs before the agent uses a tool for Edit, Write, MultiEdit, NotebookEdit, Bash, Monitor, Read, Grep, Glob and Task tool calls, executing write-custody.sh, bash-custody.sh, captain-notes-guard.sh and dispatch-guard.sh (4 commands). From dmytri/shipshape.

not rated 7 2mo ago A tokens not measured original 0BSD

PreToolUse

14

ldilov/harness-forge

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool, executing pre-tool-use.sh. From ldilov/harness-forge.

not rated 6 5mo ago A tokens not measured GPL-3.0

SessionStart

15

rhein1/fable5-codex

Hook Claude Code

One of 2 in hooks.json

Runs when a session starts on ^(startup, compact and resume)$, executing codex-context-keeper.mjs via node. From rhein1/fable5-codex.

not rated 4 yesterday A tokens not measured original MIT

SessionStart

16

mrDesign-ww/vault-os

Hook Claude Code

One of 4 in settings.json

Runs when a session starts on startup and resume, executing health-check.py. From mrDesign-ww/vault-os.

not rated 2 changed 1mo ago A tokens not measured original MIT

PreToolUse

17

mrzhangguoguo/oh-my-workbuddy

Hook Claude Code

One of 3 in hooks.json

Runs before the agent uses a tool for Bash, Agent and DeferExecuteTool tool calls, executing pre-tool-use.mjs via node (3 commands). From mrzhangguoguo/oh-my-workbuddy.

not rated 2 3mo ago A tokens not measured original MIT

PreToolUse

18

blackwell-systems/polywave-codex

Hook Claude Code

Runs before the agent uses a tool for ^Bash$, ^apply_patch$, ^mcp__lsp__(safe_edit, apply_edit, safe_apply_edit, simulate_edit, replace_symbol_body, safe_delete_symbol and commit_session)$ tool calls, running an inline shell check (3 commands). From blackwell-systems/polywave-codex.

not rated 2 5mo ago A tokens not measured

PreToolUse

19

sdfdu/evopilot

Hook Claude Code

One of 3 in hooks.json

Runs before the agent uses a tool for Bash, apply_patch and mcp__.* tool calls, executing policy_gate.py via python. From sdfdu/evopilot.

not rated 2 29d ago A tokens not measured original MIT

SessionStart

20

vignesh2027/AI-AGENT-SKILLS

Hook Claude Code

Runs when a session starts, executing session-start.sh via bash. From vignesh2027/AI-AGENT-SKILLS.

not rated 2 1mo ago A tokens not measured original MIT

PreToolUse

21

fusengine/codex

Hook Claude Code

One of 7 in hooks.json

Runs before the agent uses a tool for Bash, apply_patch, spawn_agent and multi_agent_v1.spawn_agent tool calls, executing bin.mjs via bun (3 commands). From fusengine/codex.

not rated 2 +1 4d ago A tokens not measured

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: