Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add athola/claude-night-market/plugin install abstractWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/athola/claude-night-market/create-hook)<a href="https://agentmods.dev/commands/athola/claude-night-market/create-hook"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/create-hook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/athola/claude-night-market/create-hook"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/create-hook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.02719 |
| Opus 5.5 | $0.00004 | $0.01088 |
| Sonnet 5.5 | $0.00002 | $0.00544 |
| Haiku 4.5 | $0.00001 | $0.00272 |
Grade A, and why
create-hook scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Hook Command
Creates new hooks through a structured workflow: iron-law → brainstorm → design → scaffold → validate. Uses Socratic questioning to refine rough ideas into well-designed, secure hooks before generating any files.
When To Use
Use this command when you need to:
- Creating a new hook from scratch
- Need security-first design guidance
- Want structured workflow for hook development with Socratic questioning
When NOT To Use
Avoid this command if:
- Evaluating existing hooks - use /hooks-eval instead
- Deciding where to place hooks - use hook-scope-guide skill
- Validating hook security - use /validate-hook instead
Usage
# Start with brainstorming (recommended)
/create-hook "detect when user shares sensitive files"
# Skip brainstorming if design is clear
/create-hook secret-detector --skip-brainstorm --event PreToolUse
# Create in specific plugin
/create-hook "auto-format on save" --plugin sanctum --event PostToolUse
Hook Event Types
| Event | When It Fires | Common Use Cases |
|---|---|---|
UserPromptSubmit |
User submits a prompt | Input validation, context injection |
PreToolUse |
Before tool execution | Security checks, blocking dangerous ops |
PostToolUse |
After tool completes | Logging, post-processing, notifications |
Notification |
Claude sends notification | Custom alerts, sound effects |
Stop |
Session/task ends | Cleanup, summaries, checkpoints |
SubagentStop |
Subagent completes | Aggregation, reporting |
TeammateIdle |
Teammate agent becomes idle | Work assignment, load balancing |
TaskCompleted |
Task finishes execution | Coordination, chaining, reporting |
PreCompact |
Before context compaction | Backup, preservation |
SessionStart |
Session begins | Context loading, initialization |
Workflow
Phase -1: Iron Law Interlock (Blocking)
This phase is required and cannot be skipped.
Quick Reference
- Create test file FIRST:
tests/hooks/test_${hook_name}.py - Write structural tests: Hook file exists, valid JSON/Python, registered correctly
- Run tests - capture RED state:
pytest tests/hooks/test_${hook_name}.py -v # Expected: FAILED (hook does not exist) - Capture evidence:
[E1] Command: pytest tests/hooks/test_${hook_name}.py -v Output: FAILED - FileNotFoundError Status: RED - Interlock satisfied
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 416 lines · 11 tokens per session scan A f9200fb2a6f2
create-hook is a command published in the GitHub repository athola/claude-night-market (343 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 2,719 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
analyze-codebase
Generate comprehensive analysis and documentation of entire codebase.
audit
Perform security audit on codebase.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
codex-review
Run OpenAI Codex code review on current changes or a specific branch/commit.
design-critic
Use when you want an honest read on a design instead of encouragement. What is wrong, ranked by severity, with the reason attached. Works on a screenshot, a mockup, or a described screen.