lmiranda
32bbca73ba
Debug Report (/debug-report): - Add Step 1.5: Sprint context detection based on branch and milestone - Add Step 5: Smart labeling via suggest_labels MCP tool - Update issue creation to support milestone association Debug Review (/debug-review): - Add Step 9.5: Search lessons learned before proposing fixes - Add Step 15: Verify, close issue, and optionally capture lesson Hooks: - Simplify doc-guardian hook to be truly non-blocking (15 words max) - Update code-sentinel to skip docs/config files entirely Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
16 lines
783 B
JSON
16 lines
783 B
JSON
{
|
|
"hooks": {
|
|
"PreToolUse": [
|
|
{
|
|
"matcher": "Write|Edit|MultiEdit",
|
|
"hooks": [
|
|
{
|
|
"type": "prompt",
|
|
"prompt": "[code-sentinel] SECURITY CHECK for CODE files only:\n\nSKIP entirely for: *.md, *.json, *.yml, *.yaml, *.txt, README, CHANGELOG, LICENSE, docs/*\n\nFor CODE files (.py, .js, .ts, .sh, etc.), check for:\n- eval()/exec() with unsanitized user input\n- SQL string concatenation with user data\n- shell=True with user input\n- Hardcoded real secrets (actual keys/passwords, not placeholders)\n\nResponse:\n- Security issue in code: '[code-sentinel] BLOCKED: {10 words max}'\n- Otherwise: proceed silently (say nothing)\n\nNEVER block docs/config. NEVER do lengthy analysis."
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
}
|