harness-engineering hooks

74 tagged harness-engineering, measured the same way as everything else here.

Browse within: harness 30hooks 18quality-enforcement 18agent-harness 15context-engineering 10llm-agents 10claw 8llm-model 8antigravity-skills 7brainstorming 7human-in-the-loop 7

SessionStart

25

Megaprompting/torque-loop

Hook

Part of ratchet

Runs when a session starts, running an inline shell check. From Megaprompting/torque-loop.

not rated 5 1mo ago A tokens not measured original MIT

PostToolUse

26

Megaprompting/torque-loop

Hook

Part of ratchet

Runs after a tool call finishes for Write, Edit, MultiEdit and NotebookEdit tool calls, running an inline shell check. From Megaprompting/torque-loop.

not rated 5 1mo ago A tokens not measured original MIT

Stop

27

Megaprompting/torque-loop

Hook

Part of ratchet

Runs when the agent finishes a response, running an inline shell check. From Megaprompting/torque-loop.

not rated 5 1mo ago A tokens not measured original MIT

UserPromptSubmit

28

AlexShchuka/neuro-matrix

Hook

Part of neuro-matrix

Runs when you submit a prompt, before the agent sees it, executing random-invariant.sh, self-review-preflight.sh and trail-interrupt.sh (3 commands). From AlexShchuka/neuro-matrix.

not rated 3 2mo ago A tokens not measured copy · 58% MIT

PreToolUse

29

AlexShchuka/neuro-matrix

Hook

Part of neuro-matrix

Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit, NotebookEdit, Bash and Agent tool calls, executing cycle-detector.sh, redline-guard.sh, verification-gate.sh, auto-critic.sh and skill-consult-check.sh (5 commands). From AlexShchuka/neuro-matrix.

not rated 3 2mo ago A tokens not measured copy · 66% MIT

SessionStart

31

derricktang/pm-workflow-plugin

Hook Claude Code

One of 2 in settings.json

Runs when a session starts, executing session_start_state_summary.py via python3. From derricktang/pm-workflow-plugin.

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

SessionStart

32

raelli/octowiz

Hook

Part of octowiz

Runs when a session starts, executing upgrade-check.sh and start.js via bash (2 commands). From raelli/octowiz.

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

PostToolUse

33

raelli/octowiz

Hook

Part of octowiz

Runs after a tool call finishes for Edit, Write, MultiEdit and NotebookEdit tool calls, executing bridge.py via python3. From raelli/octowiz.

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

UserPromptSubmit

34

raelli/octowiz

Hook

Part of octowiz

Runs when you submit a prompt, before the agent sees it, executing bridge.py via python3. From raelli/octowiz.

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

PreToolUse

35

iroha924/mumei

Hook

Part of mumei

Runs before the agent uses a tool for Edit, Write, MultiEdit, Bash and ExitPlanMode tool calls, executing pre-edit-guard.sh, pre-bash-guard.sh and pre-exitplan-guard.sh via bash (3 commands). From iroha924/mumei.

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

SessionStart

36

iroha924/mumei

Hook

Part of mumei

Runs when a session starts on startup, resume, startup and resume, executing session-start-status.sh and session-start-bypass-notice.sh via bash (2 commands). From iroha924/mumei.

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

SubagentStart

37

iroha924/mumei

Hook

Part of mumei

Runs when a subagent starts for ^(mumei:)?(adversarial-reviewer, design-reviewer, requirements-reviewer, security-reviewer, spec-compliance-reviewer, tasks-reviewer, issue-validator and memory-curator)$ tool calls, executing subagent-cost-log-start.sh and subagent-context-inject.sh via bash (2 commands). From…

not rated 2 3d ago A tokens not measured original 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: