appsec-engineer

appsec-engineer is a skill for Claude Code, Codex from UnitOneAI/SecuritySkills. It costs 76 tokens per session (4,499 once invoked), scanned A, original, MIT.

An application security guide for reviewing software from design through deployment. It covers application architecture, pull requests, APIs, and features that use large language models.

In plain words
What is it for?
It helps threat-model new applications, review security-sensitive code changes, assess APIs against common API risks, and examine AI features.
Why use it?
It brings security checks into design and development instead of waiting for a late penetration test or release review.

Skill for Claude CodeCodex

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 skills/unitoneai/securityskills/appsec-engineer
Any agent
npx skills add UnitOneAI/SecuritySkills --skill appsec-engineer
Clone the repo
git clone --depth 1 https://github.com/UnitOneAI/SecuritySkills

Made for: Claude Code, Codex.

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 appsec-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/unitoneai/securityskills/appsec-engineer.svg)](https://agentmods.dev/skills/unitoneai/securityskills/appsec-engineer)
Your own site
<a href="https://agentmods.dev/skills/unitoneai/securityskills/appsec-engineer"><img src="https://agentmods.dev/badge/skills/unitoneai/securityskills/appsec-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,499 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 $0.00076 $0.04499
Opus 5 $0.00038 $0.02250
Sonnet 5 $0.00015 $0.00900
Haiku 4.5 $0.00008 $0.00450

Measured 3d ago against content hash a361b760e11e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

appsec-engineer 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 3d 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.

roles/appsec-engineer/SKILL.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AppSec Engineer Role Bundle

A structured application security guide for engineers who own the security posture of applications from design through deployment. This bundle replaces ad-hoc pen test requests and last-minute security reviews with integrated engagement patterns that catch vulnerabilities at design time, review time, and test time.


When to Use

Invoke this role bundle when any of the following conditions are true:

  • New application or service launching. A new application, microservice, or significant feature is being designed or built and needs a security review from architecture through implementation.
  • Pull request with security-relevant changes. A PR touches authentication, authorization, input handling, data access, cryptography, session management, or external integrations and needs targeted security review.
  • API security assessment. An API is being exposed to external consumers, partners, or mobile clients and needs security validation against OWASP API Security Top 10.
  • AI/LLM feature review. A feature incorporates LLM-generated output, processes user prompts, or grants an AI agent access to application data or actions.

If the ask is about infrastructure security (e.g., "review our Kubernetes RBAC") or program-level maturity (e.g., "assess our overall security posture"), use the security-engineer or vciso role bundle instead. This bundle is for application-layer security work.

Skills: All skills referenced in this bundle are available: threat-modeling, secure-code-review, llm-top-10, prompt-injection, api-security, dependency-scanning, owasp-top-10-web, sast-config, agent-security.


Engagement Types

Each engagement type defines a skill sequence. Run the skills in order — each one produces outputs consumed by the next.

1. New Application Review

Trigger: New application, service, or major feature entering development. Ideally invoked at design phase, before code is written.

Read the full file on GitHub · 366 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. 3d ago First seen · 366 lines · 76 tokens per session scan A a361b760e11e

Subscribe to this mod's changes

appsec-engineer is a skill published in the GitHub repository UnitOneAI/SecuritySkills (58 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 4,499 once invoked, about $0.0004 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.