aggregate-logs
CommandGenerate LEARNINGS.md from skill execution logs over a configurable time window.
Convert Python SDK hooks to declarative rules
> /plugin marketplace add athola/claude-night-market
name: from-hook description: Convert Python SDK hooks to declarative rules
Convert Python SDK hooks to declarative hookify rules.
/hookify:from-hook <hook_file.py> # Convert single hook /hookify:from-hook --scan <hooks_dir> # Scan directory /hookify:from-hook <hook.py> -o rules.md # Output to file
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/hook_to_hookify.py" $ARGUMENTSThe script prints each hook it did not convert, with the reason, to stderr as a `Not converted:` line. It exits 1 when no hook converted. Report the generated rules and every `Not converted:` line.
1. Parses Python hook AST 2. Extracts regex patterns, string checks, startswith/endswith 3. Generates equivalent hookify rule YAML 4. Reports unconvertible hooks (network, file I/O, complex logic)
Input hook. The converter reads the hook type from the filename (`pre_tool_*.py`) or from a `PreToolUse`-style comment, as here:
# PreToolUse
import re
def hook(context):
if re.search(r"rm -rf /", context["command"]):
return {"action": "block", "message": "Dangerous!"}Output rule:
--- name: block-rm-rf event: bash pattern: 'rm -rf /' action: warn ---
Every generated rule is `action: warn`. Review it, then change it to `block` by hand where the original hook blocked.
Cannot convert hooks with:
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Generate context optimization report for skill directories
Create slash commands with brainstorming and best practices
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.