hook-creator

Name: hook-creator
Author: softspark

161stars21forks

How to install hook-creator?

softspark/ai-toolkit/hook-creator

$npx -y skills add softspark/ai-toolkit --skill hook-creator

Installs into the current project.

Summary

Create new Claude Code lifecycle hook (PreToolUse/PostToolUse/Stop/SessionStart) with bash + hooks.json. Triggers: create hook, lifecycle hook, PreToolUse, PostToolUse, hook event.

Files · 1

View on GitHub

SKILL.md

1	# Hook Creator
2
3	$ARGUMENTS
4
5	Create a new Claude Code hook following ai-toolkit conventions.
6
7	## Supported Hook Events
8
9	### Core lifecycle
10
11	\| Event \| Fires When \| Matcher \| Typical Use \|
12	\|-------\|-----------\|---------\|-------------\|
13	\| `SessionStart` \| Session begins, resumes, or clears \| `startup\\|resume\\|clear` \| Context injection, rules reminder \|
14	\| `SessionEnd` \| Session is closing \| any \| Flush logs, save transcripts \|
15	\| `UserPromptSubmit` \| User submits a prompt \| any \| Prompt governance, usage tracking \|
16	\| `Notification` \| Claude sends a notification \| any \| OS alerts, Slack pings \|
17	\| `MessageDisplay` \| Assistant message is about to be shown to the user \| any \| Transform or hide assistant message text before display \|
18
19	### Tool lifecycle
20
21	\| Event \| Fires When \| Matcher \| Typical Use \|
22	\|-------\|-----------\|---------\|-------------\|
23	\| `PreToolUse` \| Before a tool executes \| tool name (e.g. `Bash`) or `if:` rule \| Safety guards, validation, `"defer"` for headless \|
24	\| `PostToolUse` \| After a tool executes \| tool name \| Feedback loops, logging, format-on-save \|
25	\| `PostToolUseFailure` \| After a tool fails \| tool name \| Failure telemetry, recovery hints \|
26	\| `PostToolBatch` \| After a batch of tool calls completes \| any \| Batch summaries, aggregate validation \|
27
28	### Turn lifecycle
29
30	\| Event \| Fires When \| Matcher \| Typical Use \|
31	\|-------\|-----------\|---------\|-------------\|
32	\| `Stop` \| Claude finishes responding \| any \| Quality checks, session save \|
33	\| `StopFailure` \| Turn ends due to an API error (rate limit, auth) \| any \| Alerting, fallback behavior \|
34	\| `UserPromptExpansion` \| Claude expands or rewrites a submitted prompt \| any \| Prompt policy and context shaping \|
35
36	### Subagent lifecycle
37
38	\| Event \| Fires When \| Matcher \| Typical Use \|
39	\|-------\|-----------\|---------\|-------------\|
40	\| `SubagentStart` \| Subagent launches \| any \| Observability \|
41	\| `SubagentStop` \| Subagent completes \| any \| Result validation \|
42
43	### Compaction
44
45	\| Event \| Fires When \| Matcher \| Typical Use \|
46	\|-------\|-----------\|---------\|-------------\|
47	\| `PreCompact` \| Before context compaction; can block with exit 2 or `{"decision":"block"}` \| any \| Context preservation \|
48	\| `PostCompact` \| After compaction completes \| any \| Re-inject state that was summarized away \|
49
50	### Permissions & elicitation
51
52	\| Event \| Fires When \| Matcher \| Typical Use \|
53	\|-------\|-----------\|---------\|-------------\|
54	\| `PermissionRequest` \| Tool awaiting permission; can return `updatedInput` \| any \| Headless approval flows \|
55	\| `PermissionDenied` \| Auto-mode classifier denied a tool call; return `{retry: true}` to allow retry \| any \| Coach the model, log denials \|
56	\| `Elicitation` \| MCP `elicitation/create` request arrives \| any \| Intercept / override MCP UI prompts \|
57	\| `ElicitationResult` \| Elicitation response ready to be sent back \| any \| Validate / transform elicitation replies \|
58
59	### Agent Teams
60
61	\| Event \| Fires When \| Matcher \| Typical Use \|
62	\|-------\|-----------\|---------\|-------------\|
63	\| `TaskCreated` \| New task registered via `TaskCreate` \| any \| Audit, assignment routing \|
64	\| `TaskCompleted` \| Agent Teams task finished \| any \| Lint, type check, notify \|
65	\| `TeammateIdle` \| Agent Teams member idle \| any \| Completeness reminder \|
66
67	### Worktrees & environment
68
69	\| Event \| Fires When \| Matcher \| Typical Use \|
70	\|-------\|-----------\|---------\|-------------\|
71	\| `WorktreeCreate` \| Worktree is being created; `type: "http"` can return `hookSpecificOutput.worktreePath` \| any \| Provision worktree dirs \|
72	\| `WorktreeRemove` \| Worktree is being removed \| any \| Cleanup \|
73	\| `CwdChanged` \| Working directory changes during a session \| any \| Reactive env management (e.g., direnv) \|
74	\| `FileChanged` \| Tracked file is modified on disk \| any \| Re-lint, reload config \|
75	\| `ConfigChange` \| Settings / config file changed \| any \| Re-validate, warn on drift \|
76
77	### Setup / bootstrap
78
79	\| Event \| Fires When \| Matcher \| Typical Use \|
80	\|-------\|-----------\|---------\|-------------\|
81	\| `Setup` \| First-run / initialization \| any \| Project bootstrap \|
82	\| `InstructionsLoaded` \| CLAUDE.md / AGENTS.md loaded into context \| any \| Verify presence of mandatory rules \|
83
84	## Hook Handler Types
85
86	Claude Code supports five handler `type` values in `hooks.json`:
87
88	\| Type \| Purpose \| Required fields \|
89	\|------\|---------\|-----------------\|
90	\| `command` \| Run a shell script / binary \| `command` (path + args) \|
91	\| `http` \| Call a local or remote HTTP endpoint \| `url` \|
92	\| `prompt` \| Inject a prompt to the fast inline model and use its verdict \| `prompt` \|
93	\| `agent` \| Spawn a full subagent to evaluate the event (must target `Stop` / `SubagentStop`) \| `agent` (agent name) \|
94	\| `mcp_tool

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

hook-creator

161stars21forks

View on GitHub

How to install hook-creator?

softspark/ai-toolkit/hook-creator

$npx -y skills add softspark/ai-toolkit --skill hook-creator

Installs into the current project.

Summary

Create new Claude Code lifecycle hook (PreToolUse/PostToolUse/Stop/SessionStart) with bash + hooks.json. Triggers: create hook, lifecycle hook, PreToolUse, PostToolUse, hook event.

Files · 1

View on GitHub

SKILL.md

1	# Hook Creator
2
3	$ARGUMENTS
4
5	Create a new Claude Code hook following ai-toolkit conventions.
6
7	## Supported Hook Events
8
9	### Core lifecycle
10
11	\| Event \| Fires When \| Matcher \| Typical Use \|
12	\|-------\|-----------\|---------\|-------------\|
13	\| `SessionStart` \| Session begins, resumes, or clears \| `startup\\|resume\\|clear` \| Context injection, rules reminder \|
14	\| `SessionEnd` \| Session is closing \| any \| Flush logs, save transcripts \|
15	\| `UserPromptSubmit` \| User submits a prompt \| any \| Prompt governance, usage tracking \|
16	\| `Notification` \| Claude sends a notification \| any \| OS alerts, Slack pings \|
17	\| `MessageDisplay` \| Assistant message is about to be shown to the user \| any \| Transform or hide assistant message text before display \|
18
19	### Tool lifecycle
20
21	\| Event \| Fires When \| Matcher \| Typical Use \|
22	\|-------\|-----------\|---------\|-------------\|
23	\| `PreToolUse` \| Before a tool executes \| tool name (e.g. `Bash`) or `if:` rule \| Safety guards, validation, `"defer"` for headless \|
24	\| `PostToolUse` \| After a tool executes \| tool name \| Feedback loops, logging, format-on-save \|
25	\| `PostToolUseFailure` \| After a tool fails \| tool name \| Failure telemetry, recovery hints \|
26	\| `PostToolBatch` \| After a batch of tool calls completes \| any \| Batch summaries, aggregate validation \|
27
28	### Turn lifecycle
29
30	\| Event \| Fires When \| Matcher \| Typical Use \|
31	\|-------\|-----------\|---------\|-------------\|
32	\| `Stop` \| Claude finishes responding \| any \| Quality checks, session save \|
33	\| `StopFailure` \| Turn ends due to an API error (rate limit, auth) \| any \| Alerting, fallback behavior \|
34	\| `UserPromptExpansion` \| Claude expands or rewrites a submitted prompt \| any \| Prompt policy and context shaping \|
35
36	### Subagent lifecycle
37
38	\| Event \| Fires When \| Matcher \| Typical Use \|
39	\|-------\|-----------\|---------\|-------------\|
40	\| `SubagentStart` \| Subagent launches \| any \| Observability \|
41	\| `SubagentStop` \| Subagent completes \| any \| Result validation \|
42
43	### Compaction
44
45	\| Event \| Fires When \| Matcher \| Typical Use \|
46	\|-------\|-----------\|---------\|-------------\|
47	\| `PreCompact` \| Before context compaction; can block with exit 2 or `{"decision":"block"}` \| any \| Context preservation \|
48	\| `PostCompact` \| After compaction completes \| any \| Re-inject state that was summarized away \|
49
50	### Permissions & elicitation
51
52	\| Event \| Fires When \| Matcher \| Typical Use \|
53	\|-------\|-----------\|---------\|-------------\|
54	\| `PermissionRequest` \| Tool awaiting permission; can return `updatedInput` \| any \| Headless approval flows \|
55	\| `PermissionDenied` \| Auto-mode classifier denied a tool call; return `{retry: true}` to allow retry \| any \| Coach the model, log denials \|
56	\| `Elicitation` \| MCP `elicitation/create` request arrives \| any \| Intercept / override MCP UI prompts \|
57	\| `ElicitationResult` \| Elicitation response ready to be sent back \| any \| Validate / transform elicitation replies \|
58
59	### Agent Teams
60
61	\| Event \| Fires When \| Matcher \| Typical Use \|
62	\|-------\|-----------\|---------\|-------------\|
63	\| `TaskCreated` \| New task registered via `TaskCreate` \| any \| Audit, assignment routing \|
64	\| `TaskCompleted` \| Agent Teams task finished \| any \| Lint, type check, notify \|
65	\| `TeammateIdle` \| Agent Teams member idle \| any \| Completeness reminder \|
66
67	### Worktrees & environment
68
69	\| Event \| Fires When \| Matcher \| Typical Use \|
70	\|-------\|-----------\|---------\|-------------\|
71	\| `WorktreeCreate` \| Worktree is being created; `type: "http"` can return `hookSpecificOutput.worktreePath` \| any \| Provision worktree dirs \|
72	\| `WorktreeRemove` \| Worktree is being removed \| any \| Cleanup \|
73	\| `CwdChanged` \| Working directory changes during a session \| any \| Reactive env management (e.g., direnv) \|
74	\| `FileChanged` \| Tracked file is modified on disk \| any \| Re-lint, reload config \|
75	\| `ConfigChange` \| Settings / config file changed \| any \| Re-validate, warn on drift \|
76
77	### Setup / bootstrap
78
79	\| Event \| Fires When \| Matcher \| Typical Use \|
80	\|-------\|-----------\|---------\|-------------\|
81	\| `Setup` \| First-run / initialization \| any \| Project bootstrap \|
82	\| `InstructionsLoaded` \| CLAUDE.md / AGENTS.md loaded into context \| any \| Verify presence of mandatory rules \|
83
84	## Hook Handler Types
85
86	Claude Code supports five handler `type` values in `hooks.json`:
87
88	\| Type \| Purpose \| Required fields \|
89	\|------\|---------\|-----------------\|
90	\| `command` \| Run a shell script / binary \| `command` (path + args) \|
91	\| `http` \| Call a local or remote HTTP endpoint \| `url` \|
92	\| `prompt` \| Inject a prompt to the fast inline model and use its verdict \| `prompt` \|
93	\| `agent` \| Spawn a full subagent to evaluate the event (must target `Stop` / `SubagentStop`) \| `agent` (agent name) \|
94	\| `mcp_tool

People who liked this also viewed

6 picks

Type