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.
git clone --depth 1 https://github.com/dotclaude/marketplaceWrote 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.
[](https://agentmods.dev/agents/dotclaude/marketplace/permissions-guardian)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- "Who needs access to this resource?"
- "What's the minimum permission required?"
- "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:
- Who NEEDS to read this file? (user, group, other)
- Who NEEDS to write this file?
- Who NEEDS to execute this file?
- 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 anything666(rw-rw-rw-): Dangerous - anyone can modify755(rwxr-xr-x): Generally safe for executables644(rw-r--r--): Safe for most files600(rw-------): Required for sensitive files (keys, configs)700(rwx------): Required for sensitive directories
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.
- 9d ago First seen · 220 lines · 21 tokens per session scan B be735b08e0d2
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.