What is openshell-policy-advisor?

A workflow for handling denied network requests in an OpenShell sandbox, an isolated environment that blocks unapproved access. It reads the local policy, proposes the narrowest rule, waits for a decision, and retries after approval.

Use it when OpenShell reports a policy denial or when an agent needs a narrowly scoped network policy proposal.

It turns a blocked request into a controlled approval process rather than bypassing the sandbox. This helps preserve least-privilege network access while allowing required work to continue.

openshell-policy-advisor — Skill by anthropics/claude-quickstarts

About the project

Claude Quickstarts is a collection of starter projects for building applications with the Claude API, including customer support, financial analysis, and computer-use examples. Developers use them as foundations to customize for their own deployable applications, and the catalogue add-ons provide workflows for working with these quickstarts.

anthropics/claude-quickstarts · 19,117 stars · on GitHub

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.

Any agent

npx skills add anthropics/claude-quickstarts --skill policy-advisor

Clone the repo

git clone --depth 1 https://github.com/anthropics/claude-quickstarts

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anthropics/claude-quickstarts/policy-advisor/github.svg)](https://agentmods.dev/skills/anthropics/claude-quickstarts/policy-advisor)

Your own site

<a href="https://agentmods.dev/skills/anthropics/claude-quickstarts/policy-advisor"><img src="https://agentmods.dev/badge/skills/anthropics/claude-quickstarts/policy-advisor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/anthropics/claude-quickstarts/policy-advisor"><img src="https://agentmods.dev/badge/skills/anthropics/claude-quickstarts/policy-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 139 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00139
Opus 5.5	$0.00012	$0.00056
Sonnet 5.5	$0.00006	$0.00028
Haiku 4.5	$0.00003	$0.00014

Measured 3d ago against content hash d445ad84f1b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openshell-policy-advisor 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 3d 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.

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.

Origin

This is a copy

100% identical to openshell-policy-advisor — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

managed-agents/self-hosted-sandboxes/openshell-policy/sandbox/openshell-skills/policy-advisor/SKILL.md · 9 lines

What it actually says

OpenShell Policy Advisor

When a request fails with policy_denied, do not treat the denial as final if the user task still needs the request. Read /etc/openshell/skills/policy_advisor.md, inspect http://policy.local/v1/policy/current, submit the narrowest proposal to http://policy.local/v1/proposals, wait on /v1/proposals/{chunk_id}/wait?timeout=300, and retry only after approval with policy_reloaded: true.

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.

3d ago First seen · 9 lines · 29 tokens per session scan A d445ad84f1b0

Subscribe to this mod's changes

openshell-policy-advisor is a skill published in the GitHub repository anthropics/claude-quickstarts (19,117 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 139 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to openshell-policy-advisor, differing in 0 lines, and is treated as a copy.