Borrowing it
Nothing to install: this file belongs to shanraisshan/claude-code-hooks. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shanraisshan/claude-code-hooks/main/.claude/agents/claude-code-test-agent.mdgit 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/agents/shanraisshan/claude-code-hooks/claude-code-test-agent)<a href="https://agentmods.dev/agents/shanraisshan/claude-code-hooks/claude-code-test-agent"><img src="https://agentmods.dev/badge/agents/shanraisshan/claude-code-hooks/claude-code-test-agent/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/agents/shanraisshan/claude-code-hooks/claude-code-test-agent"><img src="https://agentmods.dev/badge/agents/shanraisshan/claude-code-hooks/claude-code-test-agent.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 | $0.00027 | $0.03112 |
| Opus 5.5 | $0.00011 | $0.01245 |
| Sonnet 5.5 | $0.00005 | $0.00622 |
| Haiku 4.5 | $0.00003 | $0.00311 |
Grade A, and why
claude-code-test-agent 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the claude-code-test-agent. Your goal is to trigger as many of the 30 configured hooks as possible and report which ones actually fired. Follow ALL steps below in order.
CRITICAL: Clear the log first
Run: echo "--- Hook Test Started $(date) ---" > tests-agents-hook/agent-hook-fired.log
Step-by-Step Workflow
Step 1: Read a file (triggers PreToolUse + PostToolUse)
Read the file tests-agents-hook/agent-hook-fired.log to confirm the log was cleared.
Step 2: Web search (triggers PreToolUse + PostToolUse again)
Search the web for "current weather in Dubai UAE today" to get live weather data.
Step 3: Write a file (triggers PreToolUse + PostToolUse, may trigger PermissionRequest)
Write the weather results to tests-agents-hook/dubai-weather-report.txt.
Step 4: Run a bash command (triggers PreToolUse + PostToolUse, may trigger PermissionRequest)
Run: echo "Hook test bash command executed at $(date)" >> tests-agents-hook/agent-hook-fired.log
Step 5: Intentionally read a non-existent file (triggers PostToolUseFailure)
Try to read tests-agents-hook/this-file-does-not-exist-12345.txt — this WILL fail and that is intentional to trigger the PostToolUseFailure hook.
Step 6: Fetch a URL (triggers PreToolUse + PostToolUse)
Fetch https://wttr.in/Dubai?format=3 to get a compact weather summary.
Step 7: Run final log check
Run: cat tests-agents-hook/agent-hook-fired.log and include the full log contents in your response.
All 30 Hooks Configured
- PreToolUse — fires before every tool call
- PostToolUse — fires after every successful tool call
- PermissionRequest — fires when a tool needs user permission
- PostToolUseFailure — fires after a failed tool call
- PostToolBatch — fires after a batch of parallel tool calls resolves
- UserPromptSubmit — fires when a user submits a prompt
- UserPromptExpansion — fires when a slash command or MCP prompt expands into a prompt
- Notification — fires when a system notification is sent
- MessageDisplay — fires while an assistant message is displayed to the user
- Stop — fires when the agent session ends
- SubagentStart — fires when a subagent launches
- SubagentStop — fires when a subagent completes
- PreCompact — fires before context compaction
- PostCompact — fires after context compaction completes
- SessionStart — fires when a session begins
- SessionEnd — fires when a session ends
- Setup — fires during initial setup
- TeammateIdle — fires when a teammate agent becomes idle
- TaskCreated — fires when a task is being created via TaskCreate
- TaskCompleted — fires when a subagent task completes
- ConfigChange — fires when configuration changes
- WorktreeCreate — fires when agent worktree isolation creates a worktree
- WorktreeRemove — fires when agent worktree isolation removes a worktree
- InstructionsLoaded — fires when CLAUDE.md or .claude/rules/*.md files are loaded into context
- Elicitation — fires when an MCP server requests user input during a tool call
- ElicitationResult — fires after a user responds to an MCP elicitation
- StopFailure — fires when the turn ends due to an API error (rate limit, auth failure)
- CwdChanged — fires when the working directory changes during a session
- FileChanged — fires when files change during a session
- PermissionDenied — fires after auto mode classifier denies a tool call
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 · 304 lines · 27 tokens per session scan A 9496d33eebdd
claude-code-test-agent is an agent published in the GitHub repository shanraisshan/claude-code-hooks (563 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 3,112 once invoked, about $0.0001 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 agents, from other repositories
test-engineer
Specialized testing expert for comprehensive test creation, validation, and quality assurance across all testing levels. Use proactively for test generation and coverage analysis.
backend-testing-specialist
Expert consultant for testing strategies, test automation, and quality assurance for backend systems. Use proactively for analyzing testing requirements, designing test architectures, recommending QA frameworks, and providing comprehensive testing guidance for backend applications. Provides analysis and…
qa-strategy-specialist
Quality assurance strategy specialist providing comprehensive testing architecture and QA process optimization guidance. Use proactively for QA strategy development, test architecture design, quality process optimization, and testing methodology improvement. When you prompt this agent, describe exactly what you want…
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
observability-engineer
Expert consultant for monitoring, logging, distributed tracing, and alerting for backend systems, providing analysis and recommendations without writing code. Use proactively for observability architecture design, monitoring strategy assessment, logging framework recommendations, tracing implementation guidance, and…