secure-by-default

secure-by-default is a skill for Claude Code, Codex from HalidSaglam/saglitzsecure. It costs 65 tokens per session (1,196 once invoked), scanned A, original, MIT.

A set of instructions for choosing safer default designs before writing features such as login, file uploads, API endpoints, cookies, or external-service calls.

In plain words
What is it for?
Use it while planning authentication, sessions, uploads, webhooks, browser access rules, API keys, dependencies, or Apple device permissions.
Why use it?
It addresses security decisions early, before unsafe code becomes part of a released feature. TDD is not involved; this is guidance for implementation choices.

Skill for Claude CodeCodex

Part of the saglitzsecure plugin — 4 skills, 1 MCP server 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 skills/halidsaglam/saglitzsecure/secure-by-default
Any agent
npx skills add HalidSaglam/saglitzsecure --skill secure-by-default
Clone the repo
git clone --depth 1 https://github.com/HalidSaglam/saglitzsecure

Made for: Claude Code, Codex.

Or install saglitzsecure, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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 secure-by-default

README.md
[![agentmods](https://agentmods.dev/badge/skills/halidsaglam/saglitzsecure/secure-by-default.svg)](https://agentmods.dev/skills/halidsaglam/saglitzsecure/secure-by-default)
Your own site
<a href="https://agentmods.dev/skills/halidsaglam/saglitzsecure/secure-by-default"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzsecure/secure-by-default.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,196 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 $0.00065 $0.01196
Opus 5 $0.00032 $0.00598
Sonnet 5 $0.00013 $0.00239
Haiku 4.5 $0.00006 $0.00120

Measured 2d ago against content hash 316f28a9d225, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

secure-by-default 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/secure-by-default/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Secure defaults

This skill comes in before the code is written. It is not for auditing code that already exists but for putting the right default in place the first time: a security decision fixed afterwards drags a release that already shipped along with it.

Trigger moments — when the user starts any of these, apply step 1 before they start writing code: a login/logout flow, password or token verification, a new API endpoint, storing cookies or sessions, a file upload, a request going out to an external service, receiving a webhook, adding an API key or environment variable, installing a new dependency, opening CORS on an endpoint called from the browser, loading a page template or a script, an iOS/macOS network call, Keychain use, access to the camera/location/microphone/contacts/Face ID.

1. Tie the topic to the knowledge base

Call security_guide before you suggest any code. Give topic a short phrase describing what the user is doing (for example "cookie", "CORS", "API key"). The section it returns is dated and carries primary sources; the advice comes from there, not from memory.

Compare the id field of the returned matches list against the table below. If the section you expected did not come back, ask again with a narrower word; if it still does not come back, step 2 applies.

2. If the topic is not covered, do not invent

When security_guide says the topic is not in scope in the knowledge base yet (or matches comes back empty), your answer says so too:

This topic is not covered in this tool's knowledge base. What follows are general principles and does not rest on a dated source — if you are making a critical decision, verify it against a primary source.

Then stay strictly within general principles: least privilege, deny by default, validate input at the boundary, keep secrets out of the code, encrypt data in transit. Do not invent concrete details such as version numbers, configuration keys, header names or algorithm parameters. In a security tool, plausible-looking wrong advice is decidedly worse than no advice at all: the user trusts it, closes the topic and never opens it again.

Read the full file on GitHub · 90 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 · 90 lines · 65 tokens per session scan A 316f28a9d225

Subscribe to this mod's changes

secure-by-default is a skill published in the GitHub repository HalidSaglam/saglitzsecure (0 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 1,196 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens