guardrail-checker

guardrail-checker is an agent for Claude Code from Sagargupta16/claude-skills. It costs 89 tokens per session (351 once invoked), scanned A, original, MIT.

An automated reviewer that checks code changes against development rules and best practices.

In plain words
What is it for?
Use it to audit a change or pull request and receive pass-or-fail results with details for each rule.
Why use it?
It can catch unsafe Git actions, exposed secrets, common security problems, code-quality issues, and missing pull-request preparation before review.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dev-rules plugin — 1 skill, 1 agent, 1 hook shipped together

Good fit Use it to audit a change or pull request and receive pass-or-fail results with details for each rule.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sagargupta16/claude-skills/guardrail-checker
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/Sagargupta16/claude-skills

Made for: Claude Code.

Or install dev-rules, the plugin that ships this one along with the rest of its 1 skill, 1 agent, 1 hook.

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 guardrail-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/sagargupta16/claude-skills/guardrail-checker/github.svg)](https://agentmods.dev/agents/sagargupta16/claude-skills/guardrail-checker)
Your own site
<a href="https://agentmods.dev/agents/sagargupta16/claude-skills/guardrail-checker"><img src="https://agentmods.dev/badge/agents/sagargupta16/claude-skills/guardrail-checker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for guardrail-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/sagargupta16/claude-skills/guardrail-checker"><img src="https://agentmods.dev/badge/agents/sagargupta16/claude-skills/guardrail-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 351 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 $0.00089 $0.00351
Opus 5 $0.00044 $0.00176
Sonnet 5 $0.00018 $0.00070
Haiku 4.5 $0.00009 $0.00035

Measured 11d ago against content hash b447db625c43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

guardrail-checker 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 11d 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/dev-rules/agents/guardrail-checker.md · 41 lines

What it actually says

You are a development standards checker. Verify code changes follow guardrails and best practices.

Checks

  1. Git safety:

    • No force pushes to main/master
    • No --no-verify flags in commit commands
    • No secrets staged for commit (.env, credentials, API keys)
    • Committing to feature branch, not main directly
  2. Security:

    • No hardcoded secrets in source files
    • .env.example exists if .env is gitignored
    • No SQL string concatenation
    • Input validation present at API boundaries
  3. Code quality:

    • Conventional commit format used
    • No debug/console.log statements left in production code
    • No TODO comments introduced without tracking
    • Functions under 30 lines
  4. PR readiness:

    • Changes are scoped to one logical unit
    • Tests exist for new functionality
    • No unrelated changes mixed in

Output Format

Rule Status Details
Rule name PASS/FAIL What was found

Summary: X rules passed, Y violations found

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. 11d ago First seen · 41 lines · 89 tokens per session scan A b447db625c43

Subscribe to this mod's changes

guardrail-checker is an agent published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 351 once invoked, about $0.0004 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 agents, from other repositories

manifest-curator

Review the actual Claude or Codex manifests, catalogs and pinned revisions against their own schemas. Audit by default; report evidence and uncertainty.

V-Songbird/foundry · 31 tokens

doc-consistency-reviewer

Audit plugin README parity, platform-specific benchmark evidence and community documentation against Foundry's shared rules. Read-only; report GOOD/FLAG findings.

V-Songbird/foundry · 34 tokens

the-rfc-reviewer

Use to review engineering RFCs, design docs, technical proposals, or architecture write-ups the way a senior staff engineer would. Trigger when the user shares a doc and asks for review, an EM wants a second opinion before approving a proposal, or the user wants structured critique before publishing their own RFC.

shrwnsan/vibekit-claude-plugins · 66 tokens

the-prompt-critic

Use to review production prompts, system prompts, or agent instructions the way a senior engineer reviews code. Trigger when the user shares a prompt and asks "is this good?", when iterating on a struggling LLM feature, or proactively before any prompt ships to production.

shrwnsan/vibekit-claude-plugins · 59 tokens

test-adversary

Adversarial test reviewer for consensus stress-testing. Execution environment for adversarial reviewing skills. Spawned per wave during team review. Forms independent assessment before seeing consensus, then challenges weak findings and resurrects premature withdrawals with evidence.

shopwareLabs/ai-coding-tools · 53 tokens

test-reviewer

Read-only test reviewer for Shopware 6 compliance analysis. Execution environment for reviewing and reconciling skills. Spawned per wave during team review, or by a standalone orchestrator.

shopwareLabs/ai-coding-tools · 43 tokens