security

A set of general engineering guidelines for reviewing or building application security controls. It first identifies where the application must protect data or actions, then adapts the advice to the project's technology.

In plain words
What is it for?
Use it when changing or reviewing login, permissions, input handling, APIs, file uploads, secrets, sessions, external requests, or other security-sensitive boundaries.
Why use it?
It helps prevent security work from relying on unsafe assumptions about frameworks, databases, authentication systems, or deployment platforms.

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/soden46/engineer-flow/security
Any agent
npx skills add soden46/engineer-flow --skill security
Clone the repo
git clone --depth 1 https://github.com/soden46/engineer-flow

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,822 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 $0.00025 $0.03822
Opus 5 $0.00013 $0.01911
Sonnet 5 $0.00005 $0.00764
Haiku 4.5 $0.00003 $0.00382

Measured 2d ago against content hash e4b3b7d42c57, 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 2d 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.

skills/engineer-flow/core/security/SKILL.md · 854 lines

How it starts

The opening of the file, as written. The whole thing — 854 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security

Use this skill when a task creates, changes, reviews, or fixes a security-sensitive application boundary.

The rules in this skill are framework and language agnostic.

Do not assume a specific framework, ORM, authentication library, HTTP server, database, queue, cloud provider, or deployment platform.

Core Principle

Identify the security boundary first.

Then use the safest native mechanism available in the detected project stack.

Technology-specific implementation details should be derived from project evidence, native stack mechanisms, or relevant user-installed specialist skills rather than hardcoded into this skill.

Security Review Scope

Check only areas relevant to the change.

Primary areas:

  • authentication
  • authorization
  • input validation
  • output encoding
  • request forgery protection
  • injection
  • secret handling
  • sensitive data exposure
  • file uploads
  • API security
  • rate limiting and abuse protection
  • session and token handling
  • dependency and configuration security
  • logging and error disclosure
  • unsafe redirects and outbound requests
  • serialization and deserialization
  • access to filesystem, network, subprocesses, and other privileged resources

Do not mechanically run every category for every task.

1. Trust Boundaries

Treat data crossing a trust boundary as untrusted until validated.

Common boundaries include:

  • HTTP requests
  • API payloads
  • form input
  • URL parameters
  • headers
  • cookies
  • uploaded files
  • webhooks
  • message queues
  • database content originating from users
  • external APIs
  • environment/configuration values
  • files
  • command-line arguments

Validate as close to the boundary as practical.

Validation should constrain:

  • type
  • structure
  • allowed values
  • length
  • range
  • format
  • relationships between fields

Prefer allowlists and explicit schemas over ad-hoc filtering.

Do not rely on frontend validation for server-side security.

2. Authentication

Use established authentication mechanisms provided by the project stack.

Read the full file on GitHub · 854 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. 2d ago First seen · 854 lines · 25 tokens per session scan A e4b3b7d42c57

Subscribe to this mod's changes

security is a skill published in the GitHub repository soden46/engineer-flow (3 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 3,822 once invoked, about $0.0001 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 skills, from other repositories

snip

You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.

edouard-claude/snip · 0 tokens

todos

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…

JetBrains/thinkrail · 127 tokens

writing-workflow-skills

Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

JetBrains/thinkrail · 60 tokens

reviewing-changes

Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.

JetBrains/thinkrail · 59 tokens

setting-up-a-project

Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…

JetBrains/thinkrail · 76 tokens

writing-specs

Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.

JetBrains/thinkrail · 59 tokens