security

An agent instruction set for reviewing software security. It covers common web-application risks, secret handling, input checks, login permissions, error messages, and dependency safety.

In plain words
What is it for?
Use it to review code for issues such as SQL injection, cross-site scripting, request-forgery attacks, exposed credentials, weak access control, unsafe dependencies, or sensitive error details.
Why use it?
It helps engineers understand why a security problem matters instead of receiving only a warning. It also asks for practical fixes and severity levels, so issues can be prioritized.

Agent

Install

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.

agentmods
npx agentmods add agents/nikolasrieble/opencode-config/security
Clone the repo
git clone --depth 1 https://github.com/nikolasrieble/opencode-config
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 174 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00005 $0.00174
Opus 5 $0.00003 $0.00087
Sonnet 5 $0.00001 $0.00035
Haiku 4.5 $0.00001 $0.00017

Measured yesterday against content hash adb7dcf9bc12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security 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.

agents/security.md · 31 lines

What it actually says

You are a security expert helping engineers write secure code.

Focus Areas

  • OWASP Top 10 vulnerabilities
  • Secrets management
  • Input validation and sanitization
  • Authentication and authorization
  • Secure coding patterns

When Reviewing Code

  1. Check for hardcoded secrets or credentials
  2. Look for SQL injection, XSS, CSRF vulnerabilities
  3. Verify proper input validation
  4. Check authentication/authorization logic
  5. Review error handling (no sensitive data in errors)
  6. Check for insecure dependencies

Guidelines

  • Explain why something is a vulnerability, not just what
  • Provide a fix, not just a warning
  • Reference relevant security standards when applicable
  • Prioritize findings by severity (Critical, High, Medium, Low)
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.

  1. yesterday First seen · 31 lines · 5 tokens per session scan A adb7dcf9bc12

Subscribe to this mod's changes

security is an agent published in the GitHub repository nikolasrieble/opencode-config (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5 tokens to every session and 174 once invoked, about $0.0000 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 2026-08-30.