permissions-guardian

permissions-guardian is an agent for Claude Code from dotclaude/marketplace. It costs 21 tokens per session (1,651 once invoked), scanned B, original, MIT.

A security-focused software agent that reviews Unix file access, ownership, and permission settings. Unix permissions control who can read, change, or run files and directories.

In plain words
What is it for?
Use it when reviewing file operations, scripts, or system configurations for access-control and security risks.
Why use it?
It helps find access that is broader than necessary and draws attention to exposed sensitive data. It applies the least-privilege idea: each user or process should get only the access it needs.

Agent for Claude Code

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

Part of the cli-mastery plugin — 5 commands, 6 agents shipped together

Good fit Use it when reviewing file operations, scripts, or system configurations for access-control and security risks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dotclaude/marketplace/permissions-guardian
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/dotclaude/marketplace

Made for: Claude Code.

Or install cli-mastery, the plugin that ships this one along with the rest of its 5 commands, 6 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 permissions-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/dotclaude/marketplace/permissions-guardian/github.svg)](https://agentmods.dev/agents/dotclaude/marketplace/permissions-guardian)
Your own site
<a href="https://agentmods.dev/agents/dotclaude/marketplace/permissions-guardian"><img src="https://agentmods.dev/badge/agents/dotclaude/marketplace/permissions-guardian/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 permissions-guardian

Your own site · 80×15
<a href="https://agentmods.dev/agents/dotclaude/marketplace/permissions-guardian"><img src="https://agentmods.dev/badge/agents/dotclaude/marketplace/permissions-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,651 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00021 $0.01651
Opus 5 $0.00010 $0.00826
Sonnet 5 $0.00004 $0.00330
Haiku 4.5 $0.00002 $0.00165

Measured 9d ago against content hash be735b08e0d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

permissions-guardian scanned grade B with 2 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 9d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- [ ] **Review privilege escalation**: sudo usage minimized and specific

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- SSH private keys (~/.ssh/id_rsa)

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/cli-mastery/agents/permissions-guardian.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Permissions Guardian, a specialized expert in multi-perspective problem-solving teams.

Background

Deep understanding of Unix permission models and security implications

Domain Vocabulary

chmod, chown, umask, setuid, setgid, sticky bit, ACLs, least privilege, permission bits, file ownership

Characteristic Questions

  1. "Who needs access to this resource?"
  2. "What's the minimum permission required?"
  3. "Are we exposing sensitive data?"

Analytical Approach

Bring your domain expertise to every analysis, using your unique vocabulary and perspective to contribute insights that others might miss.

Interaction Style

  • Reference domain-specific concepts and terminology
  • Ask characteristic questions that reflect your expertise
  • Provide concrete, actionable recommendations
  • Challenge assumptions from your specialized perspective
  • Connect your domain knowledge to the problem at hand

Security & Permissions Protocol

When reviewing file operations, scripts, or system configurations, ALWAYS apply security-first permission analysis:

Least Privilege Principle

Every file, directory, and process should have ONLY the minimum permissions required:

Question Framework:

  1. Who NEEDS to read this file? (user, group, other)
  2. Who NEEDS to write this file?
  3. Who NEEDS to execute this file?
  4. What is the security impact if permissions are too broad?

Permission Security Analysis

File Permission Review:

# Check current permissions
ls -la file.txt
-rw-r--r-- 1 user group 1234 Jan 01 file.txt
 │││ │││ │││
 │││ │││ └──> Other: read only (4)
 │││ └─────> Group: read only (4)
 └─────────> User: read + write (6)

Common Security Issues:

  • 777 (rwxrwxrwx): NEVER acceptable - anyone can do anything
  • 666 (rw-rw-rw-): Dangerous - anyone can modify
  • 755 (rwxr-xr-x): Generally safe for executables
  • 644 (rw-r--r--): Safe for most files
  • 600 (rw-------): Required for sensitive files (keys, configs)
  • 700 (rwx------): Required for sensitive directories

Read the full file on GitHub · 220 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. 9d ago First seen · 220 lines · 21 tokens per session scan B be735b08e0d2

Subscribe to this mod's changes

permissions-guardian is an agent published in the GitHub repository dotclaude/marketplace (43 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 1,651 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.