Best hooks

6,784 hooks are in the catalogue. These 8 are the ones that pass every gate. Every gate: original work, not a copy · security scan A or B · a licence that permits reading the source · an actively maintained repository people actually use. Order is the composite score — reputation, freshness, safety, originality, content and traction — not anyone's opinion.

#ModTypeCategoryStarsScanTokensRating
1 StopHomebrew/brewRuns when the agent finishes a response, running ./bin/brew lgtm. From Homebrew/brew. Hook Other 49k A
2 PostToolUsesigp/lighthouseRuns after a tool call finishes for Edit and Write tool calls, running echo '. From sigp/lighthouse. Hook Other 3.5k A
3 PreToolUsecozystack/cozystackRuns before the agent uses a tool for Write, Edit, MultiEdit and Bash tool calls, executing md-no-hardwrap.py. From cozystack/cozystack. Hook Other 2.2k A
4 PostToolUsejesseduffield/lazydockerRuns after a tool call finishes for Edit, Write and MultiEdit tool calls, running an inline shell check. From jesseduffield/lazydocker. Hook Other 53k A
5 UserPromptSubmitEverMind-AI/SkillCorpusRuns when you submit a prompt, before the agent sees it, executing hook.mjs via node. From EverMind-AI/SkillCorpus. Hook Other 524 A
6 PreCompactdrona23/claude-token-efficientRuns before the context is compacted, running an inline shell check. From drona23/claude-token-efficient. Hook Other 6.0k A
7 PreCompactavenoxai/avenoxbeyinRuns before the context is compacted, executing pre-compact.sh. From avenoxai/avenoxbeyin. Hook Building agents 69 A
8 PostToolUseiamfakeguru/agent-mdRuns after a tool call finishes for Write, Edit, MultiEdit, Grep and Bash tool calls, executing post-edit-verify.sh, tdd-check.sh and truncation-check.sh (3 commands). From iamfakeguru/agent-md. Hook Other 966 A

Want everything, not just what passes the gates? Browse all hooks. This shelf recomputes nightly from the measurements.