Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Scan

ASecurity

Check an explicitly requested file, directory, repository, public HTTPS URL or MCP server with Patronus, preserving scope and returning scan coverage and findings.

2 stars
0 votes
0 copies
0 views
Added 10/3/2026
ai-agentsrustgobashapisecurity

Works with

cliapimcp

Security Analysis

A100/100

Scanned 10/3/2026

$npx -y skills add patronus-protect/patronus-security-cli --skill scan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Scan?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Scan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/patronus-protect-scan/badge)](https://www.skillsdirectory.com/skills/patronus-protect-scan)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: scan
description: Check an explicitly requested file, directory, repository, public HTTPS URL or MCP server with Patronus, preserving scope and returning scan coverage and findings.
---

Use the native `patronus_scan` tool for explicit checks, keeping the user's scope:

Invoke this skill and the static scan tool only when the user explicitly asks for
that audit. Never infer a repository scan from the working directory, a file read,
or the presence of this skill. Runtime hooks scan only text that crosses their
prompt/tool/MCP result boundary.

- File: `{"kind":"file","path":"/absolute/path/file.ext"}`.
- Directory/repository: `{"kind":"directory","path":"/absolute/path"}` or `{"kind":"repo","path":"/absolute/repository"}`.
- URL: `{"kind":"url","path":"https://example.org/page"}`.
- Public MCP server: `{"kind":"mcp","path":"https://example.org/mcp"}`.
- MCP configuration: `{"kind":"mcp","path":"/absolute/config.json","server":"selected-name"}`. JSON `mcpServers` and TOML `mcp_servers` are supported. Select a name when several servers exist.

For that explicit audit, do not pre-read candidate files or fetch URLs yourself.
Pass a user-supplied relative or absolute path directly to `patronus_scan`; do not
locate, normalize, inspect, or validate it with Read, Bash, Glob, or Grep first.
The CLI resolves MCP configuration locally and sends only the public HTTPS
endpoint. It does not start stdio servers or forward private MCP credentials.
Scanning server metadata does not approve future responses or execute its tools.

`local` scans text/files on this device. `hybrid` keeps prompts local; tool/MCP results and files of at most 2048 tokens stay local, larger ones go to the API. `api` sends text to the API. Explicit URL/MCP audits always use the API, including in `local` mode; this does not change the configured processing mode.

If the native scan tool is unavailable, resolve the separately installed trusted CLI from `PATH`, outside the repository under inspection. Inspect `config print --format json`, then use `patronus-security-scanner scan KIND TARGET --format json`; for a named MCP entry add `--server NAME`. Missing CLI/setup is handled by `patronus-setup` when installation is requested.

Summarize status, supported category findings and complete/incomplete coverage. Return only safe report metadata; do not echo candidate content or process diagnostics. An `INCOMPLETE`, failed or pending scan never grants approval. Patronus is fail-open for the user's underlying tool request: if an audit is unavailable because authentication, usage, network access or the API is unavailable, continue with the requested tool under the hook's degraded context and do not claim Patronus approved it. To read a masked document from a static finding, call `patronus_read_redacted` once with its `file_id`. Runtime pending receipts use `patronus_check_result` with `scan_id`; dangerous runtime receipts use `patronus_read_redacted` with `scan_id`, without repeating the original operation.

An explicit URL scan does not automatically gate an unrelated connector's subsequent fetch. Only a verified deterministic runtime gate can protect that fetched text before model context.

Never invoke `support-us` unless the user explicitly requests it. Never fall back to a different provider silently.

Attribution

patronus-protectpatronus-protect
View sourceSee grades on GitHubMore from patronus-protect →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →