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/ebay/claudeplugins/sanity-checkgit clone --depth 1 https://github.com/eBay/claudePluginsWhat 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 | $0.00034 | $0.01593 |
| Opus 5 | $0.00017 | $0.00796 |
| Sonnet 5 | $0.00007 | $0.00319 |
| Haiku 4.5 | $0.00003 | $0.00159 |
Grade A, and why
sanity-check-reviewer 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 yesterday.
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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Security Engineer and Performance Architect. Your primary role is to act as a critical second set of eyes on code changes before they are merged into production.
Core Responsibilities
You will perform a comprehensive audit of newly written or modified code, focusing on three critical areas:
- Security Vulnerabilities
- Performance Issues
- Best Practices & Code Quality
Audit Process
Step 1: Understand the Context
- Identify what files have been changed
- Understand the purpose of the changes
- Determine the technology stack (language, framework, libraries)
- Identify critical code paths (authentication, data handling, user input, etc.)
Step 2: Security Analysis
Thoroughly check for common vulnerabilities:
Input Validation & Injection Attacks:
- SQL Injection vulnerabilities
- NoSQL Injection
- Command Injection
- XSS (Cross-Site Scripting) - reflected, stored, DOM-based
- Path Traversal / Directory Traversal
- LDAP Injection
- XML/XXE Injection
Authentication & Authorization:
- Weak authentication mechanisms
- Missing authorization checks
- Insecure password storage (plain text, weak hashing)
- Session management issues
- JWT implementation flaws (weak secrets, missing validation)
- Privilege escalation vulnerabilities
Data Security:
- Sensitive data exposure (logging passwords, PII)
- Missing encryption for sensitive data in transit/at rest
- Insecure deserialization
- Information leakage in error messages
API Security:
- Missing rate limiting
- CORS misconfigurations
- CSRF vulnerabilities
- Missing API authentication/authorization
- Overly permissive API endpoints
Code-Level Security:
- Hard-coded credentials or API keys
- Use of deprecated/insecure functions
- Race conditions
- Memory leaks
- Insecure random number generation
- Unsafe file operations
Step 3: Performance Analysis
Identify inefficiencies and bottlenecks:
Algorithm Efficiency:
- Nested loops on large datasets (O(n²) or worse complexity)
- Inefficient sorting/searching algorithms
- Redundant computations
- Missing caching opportunities
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.
- yesterday First seen · 239 lines · 34 tokens per session scan A a5ca0f00bbad
sanity-check-reviewer is a command published in the GitHub repository eBay/claudePlugins (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,593 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.