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
Hook
Runs before the agent uses a tool for Bash, Edit, Write, Read, Grep and Glob tool calls, executing loomi-bridge.mjs via node with --event. From melandlabs/openloomi.
Hook
Runs when the agent finishes a response, executing loomi-bridge.mjs via node with --event (2 commands). From melandlabs/openloomi.
Hook
Runs when the agent sends a notification for permission_prompt and elicitation tool calls, executing loomi-bridge.mjs via node with --event. From melandlabs/openloomi.
Hook
Runs when a session starts on startup, compact and compact, executing namespace-hint.sh and post-compact-auto-loop.sh (2 commands). From sd0xdev/sd0x-harness.
Hook
Runs after a tool call finishes for Edit, Write, NotebookEdit and Skill tool calls, executing post-edit-format.sh and post-skill-auto-loop.sh (2 commands). From sd0xdev/sd0x-harness.
Hook
Runs when you submit a prompt, before the agent sees it, executing user-prompt-review-guard.sh. From sd0xdev/sd0x-harness.
Hook
Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing cc10x_pretooluse_guard.py and cc10x_git_guard.py via python3 (2 commands). From romiluz13/cc10x.
Hook
Runs when a session starts on startup, resume and compact, executing cc10x_sessionstart_context.py via python3. From romiluz13/cc10x.
Hook
Runs after a tool call finishes for Edit and Write tool calls, executing cc10x_posttooluse_artifact_guard.py via python3. From romiluz13/cc10x.
Hook Claude Code
Runs before the agent uses a tool for Edit, Write, Edit and Write tool calls, running an inline shell check (2 commands). From deepklarity/harness-kit.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From deepklarity/harness-kit.
tranhieutt/software_development_department
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing prompt-context.sh, persist-memory.sh and log-skill.sh via bash (3 commands). From tranhieutt/software_development_department.
tranhieutt/software_development_department
Hook Claude Code
Runs before the agent uses a tool for Bash, Task, Write, Edit and Read tool calls, executing bash-guard.ps1, validate-commit.ps1, validate-push.ps1, circuit-guard.sh, pre-code-gate.ps1 and file-history.sh (6 commands). From tranhieutt/software_development_department.
tranhieutt/software_development_department
Hook Claude Code
Runs after a tool call finishes for Write, Edit, Bash and Task tool calls, executing log-writes.sh, extract-decisions.sh, log-commit.sh, decision-ledger-writer.sh and circuit-updater.sh via bash (5 commands). From tranhieutt/software_development_department.
raphaelchristi/harness-evolver
Hook
Runs when a session starts, executing session-start.sh via bash. From raphaelchristi/harness-evolver.
wayne930242/Reflexive-Claude-Code
Hook
Runs after a tool call finishes for Edit and Write tool calls, executing validate_frontmatter.py with --version. From wayne930242/Reflexive-Claude-Code.
Hook
Runs before the agent uses a tool for Write, Edit and MultiEdit tool calls, executing root-guard.mjs via node. From redker56/auto-harness.
Hook
Runs when a session starts on startup, resume and compact, executing harness-hook.mjs via node. From redker56/auto-harness.
Hook
Runs when a subagent starts for auto-harness:planner-clarify-agent, auto-harness:planner-clarify-parallel-agent, auto-harness:planner-spec-draft-agent, auto-harness:planner-spec-draft-parallel-agent, auto-harness:generator-draft-contract-agent, auto-harness:generator-draft-contract-parallel-agent…
jpantsjoha/ai-native-developer-experience
Hook
Runs when a session starts on startup, clear and compact, running an inline shell check. From jpantsjoha/ai-native-developer-experience.
Hook
Runs when a session starts, executing session-start.sh. From agentis-tools/ctx.
Hook
Runs after a tool call finishes for Edit and Write tool calls, executing post-tool-use.sh. From agentis-tools/ctx.
Hook
Runs when the agent finishes a response, executing stop.sh. From agentis-tools/ctx.
Hook
Runs before the agent uses a tool for Bash tool calls, executing block-push-during-sprint.ps1. From bouob/agent-harness.