Skip to content

/kit-security

Security guardrails pack — injection, secrets, path traversal, auth defaults, deserialization, untrusted-content discipline. Use when asked for a security pass or when code touches user input, secrets, or auth.

shell
$ npx -y skills add altafino/FableClaudeMDForOpus --skill kit-security --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/kit-security
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this skill.

Security guardrails pack — injection, secrets, path traversal, auth defaults, deserialization, untrusted-content discipline. Use when asked for a security pass or when code touches user input, secrets, or auth.

SKILL.md

kit-security.SKILL.md
name: kit-security
description: Security guardrails pack — injection, secrets, path traversal, auth defaults, deserialization, untrusted-content discipline. Use when asked for a security pass or when code touches user input, secrets, or auth.

Read and apply to the current task, citing rule IDs with one line of evidence as they fire:

  • docs/guardrails/SECURITY.md — SEC1–SEC8
  • docs/guardrails/TRUST.md — TR1–TR4
  • docs/guardrails/VERIFY.md — V13 (SEC4 grep quoted beside any done-claim)
Read it on GitHub ↗
Ships withfableclaudemdforopus

A portable CLAUDE.md + documentation set that makes Claude Opus / Sonnet operate as close to frontier (Fable) level as possible inside Claude Code: fewer logic errors, fewer introduced bugs, fewer wasted tokens.

Get the whole plugin, auto-invoked
Stats
6
Stars
0
Views
0
Forks
Active
Maintenance
Python
Language
24d ago
Last commit
27d ago
Created

Repo: altafino/FableClaudeMDForOpus