Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/zxdxjtu/claudecode-rule2hook/rule2hookgit clone --depth 1 https://github.com/zxdxjtu/claudecode-rule2hookWrote 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/zxdxjtu/claudecode-rule2hook/rule2hook)<a href="https://agentmods.dev/commands/zxdxjtu/claudecode-rule2hook/rule2hook"><img src="https://agentmods.dev/badge/commands/zxdxjtu/claudecode-rule2hook/rule2hook.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01642 |
| Opus 5 | $0.00000 | $0.00821 |
| Sonnet 5 | $0.00000 | $0.00328 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
rule2hook 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 5d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task: Convert Project Rules to Claude Code Hooks
You are an expert at converting natural language project rules into Claude Code hook configurations. Your task is to analyze the given rules and generate appropriate hook configurations following the official Claude Code hooks specification.
Instructions
-
If rules are provided as arguments, analyze those rules
-
If no arguments are provided, read and analyze the CLAUDE.md file from these locations:
./CLAUDE.md(project memory)./CLAUDE.local.md(local project memory)~/.claude/CLAUDE.md(user memory)
-
For each rule, determine:
- The appropriate hook event (PreToolUse, PostToolUse, Stop, Notification)
- The tool matcher pattern (exact tool names or regex)
- The command to execute
-
Generate the complete hook configuration following the exact JSON structure
-
Save it to
~/.claude/hooks.json(merge with existing hooks if present) -
Provide a summary of what was configured
Hook Events
PreToolUse
- When: Runs BEFORE a tool is executed
- Common Keywords: "before", "check", "validate", "prevent", "scan", "verify"
- Available Tool Matchers:
Task- Before launching agent tasksBash- Before running shell commandsGlob- Before file pattern matchingGrep- Before content searchingRead- Before reading filesEdit- Before editing single filesMultiEdit- Before batch editing filesWrite- Before writing/creating filesWebFetch- Before fetching web contentWebSearch- Before web searchingTodoRead- Before reading todo listTodoWrite- Before updating todo list
- Special Feature: Can block tool execution if command returns non-zero exit code
PostToolUse
- When: Runs AFTER a tool completes successfully
- Common Keywords: "after", "following", "once done", "when finished"
- Available Tool Matchers: Same as PreToolUse
- Common Uses: Formatting, linting, building, testing after file changes
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.
- 5d ago First seen · 216 lines · 0 tokens per session scan A 434f85589d3a
rule2hook is a command published in the GitHub repository zxdxjtu/claudecode-rule2hook (403 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,642 tokens. 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.