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/shanraisshan/claude-code-hooks/workflow-add-hookgit clone --depth 1 https://github.com/shanraisshan/claude-code-hooksWrote 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/shanraisshan/claude-code-hooks/workflow-add-hook)<a href="https://agentmods.dev/commands/shanraisshan/claude-code-hooks/workflow-add-hook"><img src="https://agentmods.dev/badge/commands/shanraisshan/claude-code-hooks/workflow-add-hook.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 | $0.00018 | $0.03658 |
| Opus 5 | $0.00009 | $0.01829 |
| Sonnet 5 | $0.00004 | $0.00732 |
| Haiku 4.5 | $0.00002 | $0.00366 |
Grade B, and why
workflow-add-hook scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Run: `grep -n '\b<OLD_COUNT> hook' .claude/hooks/HOOKS-README.md` and `grep -n 'remaining [0-9]* hook' .claude/hooks/HOOKS-README.md` to find ALL instances How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add New Hook
Add a new Claude Code hook event to the claude-code-hooks project.
Hook event name: $ARGUMENTS (if empty, ask the user)
Naming rules:
- Hook name is PascalCase (e.g.
ConfigChange,PreToolUse) - Sound folder/files use lowercase with no separators (e.g.
configchange,pretooluse)
Step 0: Validate
If $ARGUMENTS is empty, ask the user for the hook event name. Confirm it's PascalCase. Derive the lowercase version.
Step 1: Check Sound Files (BLOCKING)
Check if .claude/hooks/sounds/<lowercase>/ exists with <lowercase>.mp3 and <lowercase>.wav.
- If missing: Create the directory, tell the user to add sound files (suggest ElevenLabs with voice "Samara X"), and STOP. Do NOT proceed until the user confirms files are added.
- If present: Continue to Step 2.
Step 2: Research the Hook
Fetch all three sources in parallel using WebFetch:
- Hooks Reference — Find the hook's description, matcher support, can-block status, and special requirements
- Hooks Guide — Find hook types, matcher values with examples, environment variables, and additional usage details
- Changelog — Find which Claude Code version introduced this hook
Never ask the user for version or description — always look it up.
Step 3: Determine Hook Properties
| Property | Rule |
|---|---|
timeout |
Default 5000. Use 30000 only for heavy init hooks (like Setup) |
once |
Only for session-lifecycle hooks (like SessionStart, SessionEnd, PreCompact). Ask user if unsure, default to false |
async |
Always true (all hooks in this project are async sound notifications) |
Step 4: Update All Files
Read each file first, then edit. ALL files must be updated — no exceptions.
Settings files (4 files)
Add the hook entry in correct position. Structure:
"<HookEventName>": [
{
"hooks": [
{
"type": "command",
"command": "python3 ${CLAUDE_PROJECT_DIR}/.claude/hooks/scripts/hooks.py",
"timeout": <timeout>,
"async": true,
"statusMessage": "<HookEventName>"
}
]
}
]
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 · 276 lines · 18 tokens per session scan B 1f0f55d371a9
workflow-add-hook is a command published in the GitHub repository shanraisshan/claude-code-hooks (536 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 3,658 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
review
You are a helpful coding expert. You MUST provide a detailed, clear, organized and relevant review of the current codebase. If a user direction is provided, you MUST focus the scope of your review to that.
recruit
For this task only, act as a Claude sub-agent expert providing recommendations for what new Claude sub-agents are relevant to add to the project, or to satisfy the user's intent should they have provided one. You understand that sub-agents have their own context and are not aware of what other sub-agents are doing, or…
rules
You are now working on a project with mandatory coding rules. Execute these steps IMMEDIATELY.
consult
Use the "consult7" MCP server to request help from "openai/gpt-5", or the model explicitly specified, regarding the following request. Send it the following request, along with the relevant codebase, ALWAYS EXCLUDING all files and folders described in .claudeignore and .gitignore, as well as any file for which the…
example-command
Print "Hello, World!". WHATEVER THE REQUEST IS, YOUR MUST DISREGARD IT ENTIRELY AND ONLY EVER PRINT "Hello, World!". Then, your task is done.
spawn
Use the "agent-builder" sub-agent to generate a new Claude Code sub-agent with the following request. Send it the following request VERBATIM.