guardrails

guardrails is a plugin for Claude Code from melodic-software/claude-code-plugins. Its token cost is not measured, scanned A, original, MIT.

A set of safety checks that blocks risky actions such as writing secrets, bypassing Git hooks, force-pushing, discarding a worktree, or using unsafe file-writing workarounds. Git is the version-control system used to track code changes.

In plain words
What is it for?
It is for protecting coding-agent workflows from unsafe Git operations, secret writes, path mistakes, and selected command or process errors.
Why use it?
It prevents common commands and edits from accidentally exposing credentials, destroying work, or bypassing project safeguards.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: names the NotebookEdit tool.

Good fit It is for protecting coding-agent workflows from unsafe Git operations, secret writes, path mistakes, and selected command or process errors.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add melodic-software/claude-code-plugins/plugin install 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.

Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code.

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 guardrails

README.md
[![agentmods](https://agentmods.dev/badge/plugins/melodic-software/claude-code-plugins/guardrails.svg)](https://agentmods.dev/plugins/melodic-software/claude-code-plugins/guardrails)
Your own site
<a href="https://agentmods.dev/plugins/melodic-software/claude-code-plugins/guardrails"><img src="https://agentmods.dev/badge/plugins/melodic-software/claude-code-plugins/guardrails.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
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.
Security

Grade A, and why

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 today.

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/guardrails/.claude-plugin/plugin.json · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "guardrails",
  "description": "Fourteen safety guards that block secret/credential writes, hardcoded machine-specific paths, git hook-bypass attempts, irreversible git operations (force-push, reset --hard, worktree-wide checkout/restore discards), Bash file-write workarounds that circumvent Write/Edit hooks, Windows drive-root /tmp writes (POSIX /tmp, C:\\tmp, \\tmp), an EXPORTED MSYS_NO_PATHCONV / MSYS2_ARG_CONV_EXCL that unconverts a later path argument on Windows, multi-line `git commit -m` messages (an actual-newline `-m` mangles across shells; single-line `-m` passes), commit subjects and gh pr create titles that violate the repo's tracked team convention (when one is declared in .claude/source-control.md), (advisory) hallucinated CLI flags, (advisory) /plugin:skill references that do not resolve, (advisory) markdown citing a repo path the repo's own history shows was removed, (advisory, opt-in) un-throttled Workflow fan-out that risks burst 529s, and (advisory, opt-in) direct gh pr create calls bypassing this marketplace's own pull-request skill \u2014 each independently toggleable.",
  "author": {
    "name": "Melodic Software",
    "email": "[email protected]"
  },
  "license": "MIT",
  "keywords": [
    "guard",
    "security",
    "secrets",
    "hooks",
    "pretooluse",
    "git",
    "hardcoded-paths",
    "cli-flags",
    "pull-request"
  ],
  "userConfig": {
    "secret_pattern_detection_enabled": {
      "type": "boolean",
      "title": "secret-pattern-detection guard",
      "description": "Block writes containing high-confidence secret/credential patterns",
      "default": true
    },
    "hardcoded_path_check_enabled": {
      "type": "boolean",
      "title": "hardcoded-path-check guard",
      "description": "Block writes containing hardcoded machine-specific paths",
      "default": true
    },
    "block_no_verify_enabled": {
      "type": "bool

Read the full file on GitHub · 152 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. today Changed 49d4c45834d0
  2. yesterday Changed e969afa50d29
  3. 2d ago Changed 69e1dbe1a6d2
  4. 3d ago Changed 4777aa08f279
  5. 4d ago First seen · 152 lines scan A 9efc81c8d602

Subscribe to this mod's changes

guardrails is a plugin published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.