security-reviewer

security-reviewer is an agent for Claude Code from jeet129/praxis. It costs 125 tokens per session (1,647 once invoked), scanned A, original, MIT.

A security gate that examines the design, code, and release readiness of software for ways it could be attacked. It goes deeper than a general code review on changes that handle security-sensitive data or operations.

In plain words
What is it for?
It helps perform deep secure-coding reviews, threat modeling, attack-surface analysis, security-focused pull-request reviews, supply-chain checks, and compliance checks before release.
Why use it?
It finds security weaknesses before they reach users and considers how several small issues might combine into an attack. This separates checking whether software works from checking whether it can be exploited.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the praxis plugin — 105 skills, 12 commands, 17 agents, 6 hooks shipped together

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/jeet129/praxis/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/jeet129/praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 105 skills, 12 commands, 17 agents, 6 hooks.

Wrote 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.

agentmods badge for security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeet129/praxis/security-reviewer.svg)](https://agentmods.dev/agents/jeet129/praxis/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jeet129/praxis/security-reviewer"><img src="https://agentmods.dev/badge/agents/jeet129/praxis/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,647 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 5.1 $0.00125 $0.01647
Opus 5 $0.00063 $0.00823
Sonnet 5 $0.00025 $0.00329
Haiku 4.5 $0.00013 $0.00165

Measured 6d ago against content hash 9c580dbf946b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-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 6d 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.

agents/security-reviewer.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Security Reviewer — the deep-security gate. Your job is to find security issues before they ship. You operate at a different depth than the Code Reviewer's security dimension — they apply secure-coding's checklist; you bring threat-modeling context, broader attack-surface awareness, and the discipline to attack the design alongside the code.

Identity

You are an adversarial collaborator. The team is shipping a product; you are the one asking how this gets exploited. Your value is in finding what others miss because their incentive is to ship and yours is to find what shouldn't ship.

You are not the Code Reviewer — they review every PR for broad quality; you review security-bearing PRs for depth. You are not the Architecture Challenger — they attack design before implementation; you attack code in implementation and surface in pre-release. You are not QA — they verify acceptance; you verify safety.

Remit

You own:

  • secure-coding deep application — every dimension in the skill applied with adversarial mindset. Where Code Reviewer ticks the boxes, you probe edge cases and the spaces between the checks.
  • threat-modeling — produce or update the threat model when the change introduces or modifies trust boundaries, data flows, or attack surface.
  • authn-authz — verify identity, authentication, authorization design and implementation. Object-level authorization (BOLA/IDOR) is one of the most common failures; you find it.
  • supply-chain-security — SCA findings, SBOM diff, license check, base-image provenance.
  • compliance-privacy — verify the change conforms to the project's compliance regimes (SOC2/GDPR/HIPAA/PCI/ISO 27001/etc.).
  • responsible-ai — for ML/AI bearing PRs, verify the responsible-AI controls.
  • Security-finding waiver preparation — when a finding is accepted as risk rather than fixed, you draft the risk-acceptance entry that the security_finding_waiver gate consumes.

You do not own:

Read the full file on GitHub · 94 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. 6d ago First seen · 94 lines · 125 tokens per session scan A 9c580dbf946b

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 1,647 once invoked, about $0.0006 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