Hooks

Shell commands your agent runs at defined points. A hook is code, so read it before you install it.

PostToolUse

409

justxor/Harness_ru

Hook Claude Code

One of 4 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check (2 commands). From justxor/Harness_ru.

not rated 214 +7 20d ago A tokens not measured

PreToolUse

410

lobu-ai/lobu

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Edit, Write, Read and Bash tool calls, executing block-dist.sh, enforce-bun.sh and no-truncated-schema-proof.sh via bash with --show-toplevel (3 commands). From lobu-ai/lobu.

not rated 215 today A tokens not measured original Apache-2.0

PermissionRequest

411

scarce/axel

Hook Claude Code

One of 8 in settings.json

Runs when the agent asks permission for an action, running curl -s -X POST -H 'Content-Type: application/json' -d @- ht. From scarce/axel.

not rated 207 4mo ago B tokens not measured

PreToolUse

412

disler/nano-agent

Hook Claude Code

One of 9 in settings.json

Runs before the agent uses a tool, executing pre_tool_use.py via uv. From disler/nano-agent.

not rated 205 1y ago A tokens not measured

SessionStart

413

DrAshBooth/PyLOB

Hook Claude Code

One of 2 in settings.json

Runs when a session starts, running bd prime --hook-json. From DrAshBooth/PyLOB.

not rated 203 21d ago A tokens not measured

UserPromptSubmit

414

bagidea/bagidea-office

Hook Claude Code

One of 4 in settings.json

Runs when you submit a prompt, before the agent sees it, executing hook.ps1. From bagidea/bagidea-office.

not rated 213 2d ago A tokens not measured original MIT

PostToolUse

415

ayutaz/piper-plus

Hook Claude Code

One of 6 in settings.json

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing ruff-format.sh. From ayutaz/piper-plus.

not rated 204 3d ago A tokens not measured original MIT

PostToolUse

416

roboco-io/awesome-vibecoding

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, executing translate-readme.sh. From roboco-io/awesome-vibecoding.

not rated 202 +1 1mo ago A tokens not measured copy · 41% CC0-1.0

PostToolUse

417

pproenca/dot-skills

Hook Codex

One of 2 in hooks.json

Runs after a tool call finishes for Edit tool calls, running an inline shell check. From pproenca/dot-skills.

not rated 202 +1 20d ago A tokens not measured original MIT

PreToolUse

418

iterate/iterate

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing pr-guidance-gate.sh. From iterate/iterate.

not rated 201 +1 yesterday A tokens not measured AGPL-3.0

PreToolUse

419

paladini/harness-score

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing guard-shell.js. From paladini/harness-score.

not rated 394 3d ago A tokens not measured copy · 44% MIT

PreCompact

420

adrianco/retort

Hook Claude Code

One of 3 in settings.json

Runs before the context is compacted, running bd prime. From adrianco/retort.

not rated 201 today A tokens not measured copy · 100% Apache-2.0

PostToolUse

421

tsubotax/melta-ui

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Write and Edit tool calls, executing hook-check-rule.sh via bash. From tsubotax/melta-ui.

not rated 196 today A tokens not measured original MIT

PreToolUse

422

mpecan/tokf

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing pre-tool-use.sh. From mpecan/tokf.

not rated 196 +1 2d ago A tokens not measured original MIT

PostToolUse

423

DeL-TaiseiOzaki/claude-code-orchestra

Hook Claude Code

One of 7 in settings.json

Runs after a tool call finishes for Task, Bash, Edit and Write tool calls, executing check-codex-after-plan.py, post-bash-check.py, lint-on-save.py and post-implementation-review.py via python3 (4 commands). From DeL-TaiseiOzaki/claude-code-orchestra.

not rated 194 +1 changed today A tokens not measured original MIT

SessionStart

424

sibartlett/Geo

Hook Claude Code

One of 2 in settings.json

Runs when a session starts, executing session-start.sh. From sibartlett/Geo.

not rated 192 4d ago A tokens not measured LGPL-3.0

PreCompact

425

alexeykrol/claude-code-starter

Hook Claude Code

One of 5 in settings.json

Runs before the context is compacted, executing pre-compact.sh via bash. From alexeykrol/claude-code-starter.

not rated 192 1mo ago A tokens not measured

UserPromptSubmit

426

TheBushidoCollective/han

Hook Claude Code

One of 3 in settings.json

Runs when you submit a prompt, before the agent sees it, running han hook dispatch UserPromptSubmit. From TheBushidoCollective/han.

not rated 193 +2 11d ago A tokens not measured

PreToolUse

427

zekiriabd/SDD-Pro

Hook Claude Code

One of 6 in settings.json

Runs before the agent uses a tool for Edit, Write, MultiEdit, Bash, Glob, Agent and Skill tool calls, running an inline shell check (12 commands). From zekiriabd/SDD-Pro.

not rated 191 +15 2d ago A tokens not measured original Apache-2.0

SessionStart

428

77wliNd/aemeath_withclaude

Hook Claude Code

One of 2 in settings.json

Runs when a session starts, running an inline shell check. From 77wliNd/aemeath_withclaude.

not rated 189 +3 3mo ago A tokens not measured original MIT

PostToolUse

429

lylo/pagecord

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From lylo/pagecord.

not rated 187 today A tokens not measured

PreToolUse

430

fullselfbrowsing/FSB

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash, Read and Glob tool calls, running an inline shell check (2 commands). From fullselfbrowsing/FSB.

not rated 188 +1 today A tokens not measured original MIT

PostToolUse

431

kid-sid/claude-spellbook

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for WebSearch and WebFetch tool calls, executing capture-web-finding.js via node. From kid-sid/claude-spellbook.

not rated 188 1mo ago A tokens not measured original MIT

PreToolUse

432

mag123c/toktrack

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Skill, Edit and Write tool calls, executing implement-detector.sh, skill-chain-detector.sh and implement-guard.sh via bash (3 commands). From mag123c/toktrack.

not rated 188 yesterday A tokens not measured copy · 42% MIT

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: