Skip to content

jaktestowac/awesome-copilot-for-testers / plugins/creating-hooks/skills/creating-hooks

creating-hooks

Verified

Creates GitHub Copilot hooks for VS Code using `hooks.json`, supporting scripts, and companion docs. Use when automating deterministic checks, pre/post tool policies, or reusable hook packs that need safe defaults, observability, and clear installation guidance.

resources/hook-example-pack.md

View on GitHub
# Hook Example Pack: Block Destructive Shell Commands

This example shows a conservative safety hook that blocks obviously destructive shell commands before they run.
It is meant as a pattern for dangerous-command protection, not as a universal production policy.

## `README.md`

```md
# Block Destructive Shell Commands

This hook denies clearly destructive terminal commands such as `rm -rf`, `git reset --hard`, and drive-wide delete patterns before they are executed.
Use it in shared workspaces where accidental destructive shell usage would be costly.

## Behavior

- Event: `preToolUse`
- Mode: `deny`
- Timeout: `10` seconds
- Default action when uncertain: `allow`

## Installation

- Copy this folder to `.github/hooks/block-destructive-shell/`
- Review the command patterns before enabling it in a repository
- Adjust the allowed and denied commands to fit your team's workflow

## Notes

- This hook intentionally targets only a small set of obvious destructive commands
- If your environment uses custom wrappers, update the pattern matching accordingly
- Always return a human-readable denial reason
```

## `hooks.json`

```json
{
  "version": 1,
  "hooks": {
    "preToolUse": [
      {
        "type": "command",
        "command": "bash scripts/block-destructive-shell.sh",
        "windows": "powershell -File scripts\\block-destructive-shell.ps1",
        "cwd": ".github/hooks/block-destructive-shell",
        "timeoutSec": 10,
        "comment": "Block obviously destructive shell commands before execution"
      }
    ]
  }
}
```

## `scripts/block-destructive-shell.ps1`

```powershell
$payload = [Console]::In.ReadToEnd() | ConvertFrom-Json
$toolArgs = $payload.toolArgs
$commandText = ''

if ($null -ne $toolArgs.command) {
  $commandText = [string]$toolArgs.command
} else {
  $commandText = $toolArgs | ConvertTo-Json -Compress
}

$dangerPattern = '(?i)rm\s+-rf|git\s+reset\s+--hard|del\s+/s|format\s+[a-z]:'

if ($commandText -match $dangerPattern) {
  @{
    permissionDecision = 'deny'
    permissionDecisionReason = 'Blocked a clearly destructive shell command. Use a safer scoped command or ask for an explicit exception.'
  } | ConvertTo-Json -Compress
}
```

## `scripts/block-destructive-shell.sh`

```bash
#!/usr/bin/env bash
set -euo pipefail

payload="$(cat)"
command_text="$(printf '%s' "$payload" | jq -cr '.toolArgs.command // .toolArgs')"

if printf '%s' "$command_text" | grep -Eiq 'rm[[:space:]]+-rf|git[[:space:]]+reset[[:space:]]+--hard|del[[:space:]]+/s|format[[:space:]][A-Za-z]:'; then
  printf '%s\n' '{"permissionDecision":"deny","permissionDecisionReason":"Blocked a clearly destructive shell command. Use a safer scoped command or ask for an explicit exception."}'
fi
```

## Why this example is useful

- it targets a narrow, high-confidence policy
- it returns a clear denial reason
- it shows how `README.md`, `hooks.json`, and scripts stay aligned
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall