Autonomous Agents hooks

Wania-Kazmi/claude-code-autonomous-agent-workflow

Hook Claude Code

One of 5 in settings.json

Runs when the agent finishes a response, executing skill-enforcement-stop.sh, claudeception-activator.sh and sync-todos.py (3 commands). From Wania-Kazmi/claude-code-autonomous-agent-workflow.

markmhendrickson/ateles

Hook Claude Code

One of 6 in settings.json

Runs before the agent uses a tool for Edit, Write, NotebookEdit and Bash tool calls, executing sibling_repo_worktree_guard.py and gmail_send_gate.py via python3 (2 commands). From markmhendrickson/ateles.

markmhendrickson/ateles

Hook Claude Code

One of 6 in settings.json

Runs when a session starts on startup, resume, clear, compact and compact, executing ateles-session-start.sh, session_start.py and reinject_working_method.py (3 commands). From markmhendrickson/ateles.

markmhendrickson/ateles

Hook Claude Code

One of 6 in settings.json

Runs after a tool call finishes for ^mcp__ccd_session__spawn_task$ tool calls, executing spawn_task_neotoma_pairing.py via python3. From markmhendrickson/ateles.

zkysar1/Claude-Mind

Hook Claude Code

One of 9 in settings.json

Runs before the agent uses a tool for Read, Skill, Bash, ScheduleWakeup, Write, Edit and MultiEdit tool calls, executing context-reads-gate.sh, task-output-read-advisory.sh, context-reads-skill-gate.sh, utilization-gate.sh, bash-agent-inject.sh, bash-path-resolution-hook.sh, bare-bash-authoring-gate.sh…

zkysar1/Claude-Mind

Hook Claude Code

One of 9 in settings.json

Runs after a tool call finishes for Read, Write, Edit, MultiEdit, Bash, WebFetch and WebSearch tool calls, executing context-reads-record.sh, tree-write-fence.sh, context-reads-invalidate.sh, tree-sync-check.sh, skill-stdin-json-lint.sh, lock-symmetry-lint.sh, evolution-record.sh, owncloud-push-on-write.sh…

zkysar1/Claude-Mind

Hook Claude Code

One of 9 in settings.json

Runs when you submit a prompt, before the agent sees it, executing user-prompt-retrieval-inject.sh via bash. From zkysar1/Claude-Mind.

punt-labs/beadle

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing no-edit-on-main.sh, no-gh-watch.sh and no-push-to-main.sh via bash (3 commands). From punt-labs/beadle.

Enovatr-Labs/SpecRoute

Hook Claude Code

One of 3 in hooks.json

Runs when a session starts, executing session-start-status.sh via bash. From Enovatr-Labs/SpecRoute.

Enovatr-Labs/SpecRoute

Hook Claude Code

One of 3 in hooks.json

Runs before the agent uses a tool for Bash tool calls, executing pre-bash-sanitize.sh via bash. From Enovatr-Labs/SpecRoute.

Enovatr-Labs/SpecRoute

Hook Claude Code

One of 3 in hooks.json

Runs after a tool call finishes for Write and Edit tool calls, executing post-edit-frontmatter.sh via bash. From Enovatr-Labs/SpecRoute.

richer-richard/cc-research

Hook

Runs when the agent finishes a response, executing audit.py via python3. From richer-richard/cc-research.

Sibyl-Research-Team/AutoResearch-SibylSystem

Hook

Runs after a tool call finishes for Bash tool calls, executing on-bash-complete.sh via bash. From Sibyl-Research-Team/AutoResearch-SibylSystem.

Sibyl-Research-Team/AutoResearch-SibylSystem

Hook

Runs when a session starts, executing on-session-start.sh via bash. From Sibyl-Research-Team/AutoResearch-SibylSystem.

Sibyl-Research-Team/AutoResearch-SibylSystem

Hook

Runs when the agent finishes a response, executing on-stop.sh via bash. From Sibyl-Research-Team/AutoResearch-SibylSystem.

dork-labs/dorkos

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing file-guard.mjs, git-guard.mjs and process-guard.mjs with --show-toplevel (3 commands). From dork-labs/dorkos.

dork-labs/dorkos

Hook Claude Code

Runs after a tool call finishes for Write, Edit, MultiEdit and Write tool calls, executing typecheck-changed.sh, lint-changed.sh, check-any-changed.mjs and spec-status-sync.sh with --show-toplevel (4 commands). From dork-labs/dorkos.

dork-labs/dorkos

Hook Claude Code

Runs when the agent finishes a response, executing create-checkpoint.sh, check-docs-changed.sh and format-changed.sh with --show-toplevel (3 commands). From dork-labs/dorkos.