ss-guardrails

ss-guardrails is a skill for Claude Code from lbk-open/super-spec. It costs 70 tokens per session (511 once invoked), scanned A, original, Apache-2.0.

A reference library of safety and code-quality checklists for coding and review workflows. It includes general guidance plus rules for languages and platforms such as Java, Go, C++, web development, Android, iOS, and Flutter.

In plain words
What is it for?
Use it as supporting guidance while writing or reviewing code in one of its covered languages or platforms.
Why use it?
It gives coding agents consistent checks for security, testing, error handling, concurrency, and platform-specific mistakes. It is consulted by other workflows rather than run as a standalone task.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the super-spec plugin — 20 skills shipped together

Good fit Use it as supporting guidance while writing or reviewing code in one of its covered languages or platforms.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lbk-open/super-spec/ss-guardrails
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.

Any agent
npx skills add lbk-open/super-spec --skill ss-guardrails
Clone the repo
git clone --depth 1 https://github.com/lbk-open/super-spec

Made for: Claude Code.

Or install super-spec, the plugin that ships this one along with the rest of its 20 skills.

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 ss-guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/lbk-open/super-spec/ss-guardrails.svg)](https://agentmods.dev/skills/lbk-open/super-spec/ss-guardrails)
Your own site
<a href="https://agentmods.dev/skills/lbk-open/super-spec/ss-guardrails"><img src="https://agentmods.dev/badge/skills/lbk-open/super-spec/ss-guardrails.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 511 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 $0.00070 $0.00511
Opus 5 $0.00035 $0.00255
Sonnet 5 $0.00014 $0.00102
Haiku 4.5 $0.00007 $0.00051

Measured 8d ago against content hash 48d88f11f615, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ss-guardrails 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 8d 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/ss-guardrails/SKILL.md · 35 lines

What it actually says

Guardrails

This skill is a reference library, not a workflow. Other skills read it at the point where they need to write, change, or review code; it has no standalone "run" behavior of its own.

What's Here

File Covers Read When
core.md Security baseline, code-review dimensions and severity levels, unit-testing principles, and anti-mistake rules for AI coding agents Always — every coding or review task
java.md Java exception handling and concurrency anti-patterns, JVM testing pitfalls Project is Java/Kotlin/JVM
go.md Go error handling and testing pitfalls Project is Go
cpp.md C++ memory safety, concurrency, error handling, and testing pitfalls Project is C++
web.md Frontend/Node security and quality pitfalls Project is TypeScript/JavaScript/web
android.md Android-specific safety and quality pitfalls Project is Android/Kotlin
ios.md iOS-specific safety and quality pitfalls Project is iOS/Swift
flutter.md Flutter/Dart-specific safety and quality pitfalls Project is Flutter

How to Use This

  1. Detect the project's primary language/stack (build files, file extensions, existing code) or ask if it's ambiguous.
  2. Read core.md in full — it applies regardless of stack.
  3. Read the one or two language files that match the project's stack. Skip the rest.
  4. Apply the checklists while writing code, and re-check against them during review, before claiming a task complete.

Treat this as read-only reference material: load it into context at the moment it's needed, apply it, and don't copy its contents into the user's repository. It carries no user-specific configuration and produces no output files of its own.

Failure Handling

If the project's stack isn't covered by any language file here, fall back to core.md alone and note the gap to the user rather than guessing at stack-specific rules that don't exist yet.

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 35 lines · 70 tokens per session scan A 48d88f11f615

Subscribe to this mod's changes

ss-guardrails is a skill published in the GitHub repository lbk-open/super-spec (1 stars, last pushed 16d ago), licensed Apache-2.0. It adds 70 tokens to every session and 511 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

audit

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

oliver-kriska/claude-elixir-phoenix · 35 tokens

review

Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing.

oliver-kriska/claude-elixir-phoenix · 34 tokens

pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 59 tokens

phx-pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 61 tokens

boundaries

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

oliver-kriska/claude-elixir-phoenix · 33 tokens

challenge

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.

oliver-kriska/claude-elixir-phoenix · 34 tokens