security-init

security-init is a command for Claude Code from AratKruglik/claude-sdlc. It costs 43 tokens per session (1,408 once invoked), scanned A, original, MIT.

A command that creates project-specific security guidance files based on the technology stack in use. These files are read by a security-review add-on when checking the project.

In plain words
What is it for?
Use it after installing or changing stack add-ons, when updating security guidance, or to prepare security rules before the security-review add-on is installed.
Why use it?
It gives security checks rules that match the current stack and keeps those rules in the project where the reviewer can find them. It can also show what would be written without changing files.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

Part of the sdlc plugin — 3 skills, 5 commands, 5 agents shipped together

Good fit Use it after installing or changing stack add-ons, when updating security guidance, or to prepare security rules before the security-review add-on is installed.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/aratkruglik/claude-sdlc/security-init
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.

Clone the repo
git clone --depth 1 https://github.com/AratKruglik/claude-sdlc

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 3 skills, 5 commands, 5 agents.

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-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/aratkruglik/claude-sdlc/security-init.svg)](https://agentmods.dev/commands/aratkruglik/claude-sdlc/security-init)
Your own site
<a href="https://agentmods.dev/commands/aratkruglik/claude-sdlc/security-init"><img src="https://agentmods.dev/badge/commands/aratkruglik/claude-sdlc/security-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00043 $0.01408
Opus 5 $0.00022 $0.00704
Sonnet 5 $0.00009 $0.00282
Haiku 4.5 $0.00004 $0.00141

Measured 5d ago against content hash 22a2d1616392, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

security-init 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 5d 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.

plugins/sdlc/commands/security-init.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdlc:security-init

One-time (re-runnable) command that writes stack-specific security rules into .claude/security-patterns.yaml and .claude/claude-security-guidance.md in the current project. These files are read automatically by the security-guidance plugin — it only reads from the project's .claude/ directory, never from plugin install paths.

Run this command after installing security-guidance, when changing stack plugins, or when updating the marketplace (re-running regenerates the managed block only).

Prerequisites

  • security-guidance@claude-plugins-official should be installed and active. If it is not installed, this command still materializes the files (they will be ready when the plugin is installed later) — it prints a reminder at the end.
  • The current directory must be a project root (contains .claude/ or the command creates it).

Arguments

  • --dry-run: print what would be written without modifying any files.

Algorithm

1. Detect active stack plugins

Same detection logic as /sdlc:list-stacks — find all installed stack.md files and evaluate their detect rules against the current working directory. Collect the winning plugin(s). Always include:

  • sdlc core (base patterns apply to every project)
  • js-foundation (if any JS/TS stack is active)

2. Collect security-patterns fragments

For each active plugin (sdlc core first, then js-foundation, then stack plugins in priority order):

  • Read ~/.claude/plugins/cache/{plugin_path}/security-patterns.yaml if it exists.
  • Parse the patterns: array.
  • Tag each rule with _source: {plugin_name} for traceability (written as a comment in the output).
  • De-duplicate by rule_name (first occurrence wins — higher-priority plugin wins).

3. Merge into .claude/security-patterns.yaml

The target file uses a managed block delimited by:

# >>> sdlc-marketplace managed (do not edit inside this block) >>>
# <<< sdlc-marketplace managed <<<

If the file does not exist: create it with only the managed block containing all collected rules.

Read the full file on GitHub · 153 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. 5d ago First seen · 153 lines · 43 tokens per session scan A 22a2d1616392

Subscribe to this mod's changes

security-init is a command published in the GitHub repository AratKruglik/claude-sdlc (33 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 1,408 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 2026-09-03.