Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Checking A Call Against Policy

BSecurity

Find out whether Session Sitter will allow a tool call, and which written clause decides it, BEFORE running it. Use when about to run something plausibly governed — a push, a deploy, a migration, anything touching secrets or infrastructure — or when the user asks what the policy allows, or why a call was denied.

7 stars
0 votes
0 copies
0 views
Added 9/20/2026
developmentgoshellbashnodegit

Works with

cli

Security Analysis

B75/100
criticalAccesses sensitive system or user directories

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add eranra/session-sitter --skill checking-a-call-against-policy --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Checking A Call Against Policy?

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

Security grade badge for Checking A Call Against Policy
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/eranra-checking-a-call-against-policy/badge)](https://www.skillsdirectory.com/skills/eranra-checking-a-call-against-policy)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: checking-a-call-against-policy
description: Find out whether Session Sitter will allow a tool call, and which written clause decides it, BEFORE running it. Use when about to run something plausibly governed — a push, a deploy, a migration, anything touching secrets or infrastructure — or when the user asks what the policy allows, or why a call was denied.
---

# Checking a call against the policy

Run the check. Do not reason about the policy from memory: the corpus changes, and the artifact this
session is pinned to is the only thing that decides.

    node "${CLAUDE_PLUGIN_ROOT}/lib/policy/cli.js" explain Bash --command '<the exact command>'

For a tool that is not a shell, pass the whole input instead:

    node "${CLAUDE_PLUGIN_ROOT}/lib/policy/cli.js" explain Write --input '{"file_path":"/etc/hosts"}'

Read the result as three facts:

- **WOULD ALLOW** — proceed. The rung says whether a clause allowed it or it was simply read-only.
- **WOULD DENY, with a rewrite** — run the rewritten form. This is the common case and it is not a
  negotiation; the rewrite is what the practices already say is acceptable.
- **WOULD DENY, no rewrite** — stop and tell the user, quoting the clause citation. Do not look for a
  variant that evades the pattern. A clause with a `Match:` line will catch the variant too, and one
  that does not is exactly the clause a human needs to hear about.

**WOULD ASK** means nothing deterministic covers it, so the decision goes to the classifier or back
to the user. Exit code 1 with "no policy is loaded" means no practices are configured — say so
rather than treating it as permission.

This command decides nothing. The `PermissionRequest` hook decides, and it will decide again when you
actually run the call. If the two ever disagree, that is a bug worth reporting — say so rather than
working around it.

To *change* what the policy says, see the `writing-practices` skill. Editing a clause to unblock
yourself is a reviewed change to a git-tracked file, not a workaround.

Attribution

eranraeranra
View sourceMore from eranra →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

281612 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2132 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →