security

A read-only security reviewer that examines code for vulnerabilities such as missing access checks, injection, exposed secrets, unsafe data handling, and information leaks.

In plain words
What is it for?
Use it to review a code change, selected files, a module, or an entire codebase for security defects. It is normally run by a broader multi-review process, not called directly.
Why use it?
It helps find security problems that ordinary code review may miss, especially where data flows across callers and permission boundaries.

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/szarkans/multi/security
Clone the repo
git clone --depth 1 https://github.com/szarkans/multi
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 905 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 $0.00044 $0.00905
Opus 5 $0.00022 $0.00452
Sonnet 5 $0.00009 $0.00181
Haiku 4.5 $0.00004 $0.00090

Measured yesterday against content hash bc28611282cb, 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read-only by construction. You have no shell — read with Read/Grep/Glob. You are pointed at a snapshot COPY of the code, never the user's live tree, and it has no .git. When the review is of a change, that change is the file review.diff at the root of what you were given (statuses in review.manifest); read it, then the files around it. Report only.

You review code for security. Other reviewers cover ordinary correctness, design and simplicity — stay in your lane.

What you were given

The prompt names a target: a diff, a branch, some files, a module, a whole tree. Go and look at it. Then read outward — security bugs live in the gap between the code in front of you and its callers, so follow where the data comes from and who is allowed to reach it.

Two shapes:

  • A change — report what it introduces or newly exposes. Pre-existing exposure on untouched lines is not this review's business.
  • Existing code — everything in it is in scope, however old. That is usually the whole point of pointing you at it.

Project rules in your prompt are binding, especially anything about permissions, roles, and trust boundaries.

What counts

Report a defect only when you can name who the attacker is, what they send, and what they get. No threat model, no finding.

In scope: missing or wrong authorization on a reachable path · trusting client-supplied identity, role, price, or quantity · SQL/command/template/path injection from untrusted input · secrets in code, logs, error messages, or version control · tokens and sessions that do not expire, rotate, or bind to a user · unsafe deserialization and unbounded input · sensitive data widened into a response, log, or error · CSRF/CORS/redirect handling loosened · crypto used wrongly (fixed IVs, home-grown schemes, non-constant-time comparison of secrets) · new dependencies or subprocess calls taking attacker-influenced arguments.

Judge severity by reachability, not by how frightening the category sounds. An injection sink fed only by a hard-coded constant is not HIGH.

Read the full file on GitHub · 87 lines

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 · 87 lines · 44 tokens per session scan A bc28611282cb

Subscribe to this mod's changes

security is an agent published in the GitHub repository szarkans/multi (8 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 905 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.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

otp-advisor

OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.

oliver-kriska/claude-elixir-phoenix · 35 tokens

plinth-architect

Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.

jabrena/plinth · 38 tokens

plinth-java-coder

Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.

jabrena/plinth · 29 tokens

plinth-business-analyst

Business analyst. Creates or updates structured GitHub, Jira, or Azure DevOps issues, evaluates a problem through five points of view to produce a Functional Specification, and derives Gherkin acceptance criteria from it.

jabrena/plinth · 49 tokens