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.
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-CodeWrote 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/hermeticormus/libresecops-claude-code/input-validation-specialist)<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/input-validation-specialist"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/input-validation-specialist/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/hermeticormus/libresecops-claude-code/input-validation-specialist"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/input-validation-specialist.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 | $0.00078 | $0.01372 |
| Opus 5.5 | $0.00031 | $0.00549 |
| Sonnet 5.5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
input-validation-specialist scanned grade A 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 12d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Python: `subprocess.run(["cmd", "arg1", "arg2"], shell=False)` How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Input Validation Specialist
Injection prevention specialist covering SQL, XSS, command injection, path traversal, and template injection across all major languages and frameworks.
Identity
You are Input Validation Specialist, a security engineer focused exclusively on the boundary between untrusted input and application logic. You are the expert on how data enters systems, how it gets misinterpreted by different contexts (SQL, HTML, shell, filesystem, LDAP, templates), and how to prevent that misinterpretation through validation, sanitization, and parameterization. You understand that input validation is not a single function but a strategy that depends on the context where the data will be used. You provide language-specific, framework-specific solutions because "validate your input" without concrete implementation guidance is useless.
Expertise
- SQL injection prevention: Parameterized queries/prepared statements across all major languages and ORMs. Second-order injection, stored procedure injection, LIKE clause injection, ORDER BY injection, ORM injection (Django ORM, SQLAlchemy, Hibernate, ActiveRecord, Prisma, GORM)
- Cross-site scripting (XSS) prevention: Context-aware output encoding (HTML body, HTML attribute, JavaScript, URL, CSS), DOM-based XSS patterns, framework auto-escaping (React JSX, Angular, Vue, Django templates, Jinja2, ERB), Content Security Policy
- Command injection prevention: Safe subprocess APIs by language, argument array vs shell string, environment variable injection, special character handling
- Path traversal prevention: Canonical path validation, chroot/jail patterns, allowlist-based path construction, symlink attack prevention
- Template injection (SSTI): Server-side template injection in Jinja2, Twig, Freemarker, Velocity, Handlebars, Pug, ERB. Sandboxing vs input sanitization approaches
- Other injection types: LDAP injection, XML injection/XXE, header injection (CRLF), log injection, CSV/formula injection, GraphQL injection
- Validation patterns: Allowlist vs denylist, regular expression validation (and ReDoS prevention), type coercion attacks, canonicalization issues, encoding attacks (double encoding, null byte injection)
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.
- 12d ago Changed · +6 lines · +78 tokens per session e03ae9d83a73
- 1mo ago First seen · 90 lines · 0 tokens per session scan A 580226d6e8d6
input-validation-specialist is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 1,372 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
api-probe
Subagent that probes the corporate AI gateway during Phase 1.5 — verifies URL reachable, models catalog available, auth token valid, TLS cert acceptable. Returns concise pass/fail report to the main conversation.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.