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

Openrind Shell

ASecurity

Launch and diagnose the required Haloop-routed PostgreSQL FUSE runtime in Openrind Desktop.

3 stars
0 votes
0 copies
0 views
Added 9/26/2026
ai-agentsshellbashsqldatabase

Works with

claude codecli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add openrind/openrind-shell --skill openrind-shell --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Openrind Shell?

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

Security grade badge for Openrind Shell
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/openrind-openrind-shell/badge)](https://www.skillsdirectory.com/skills/openrind-openrind-shell)

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: openrind-shell
description: Launch and diagnose the required Haloop-routed PostgreSQL FUSE runtime in Openrind Desktop.
disable-model-invocation: false
user-invocable: true
allowed-tools: Read, Bash, Grep, Glob
argument-hint: [optional: sandbox name or workspace ID]
---

# Openrind Shell

## Supported launch flow

1. Configure PostgreSQL and the upstream provider credential in Desktop Settings.
2. In **Sandboxes**, choose **New sandbox → Claude Code** (or OpenClaw).
3. Desktop registers the scoped Haloop provider, creates the agent-home named
   volume, initializes FUSE, and issues a signed conversation context.
4. Select an existing sandbox to return to its live session. After `/exit`, use
   **Reconnect** for a new signed launch. Keep the agent-home volume for history.

Do not invent a provider ID for a standalone CLI launch. Never use
`--auto-providers`, a direct Anthropic provider, or an unsigned `claude` command
as a substitute. Missing Haloop readiness blocks launch; recovery uses Desktop's
restart/reconnect controls, never a direct-provider fallback.

## Diagnostics

Read `README.md` and `openrind-desktop/apps/desktop/OPENRIND_SHELL.md` for the
current flow and `BUILD.md` for source builds. Do not rebuild NVIDIA's base.
Never print database URLs or provider keys, or pass provider keys through `--env`.

Use the paired patched CLI and gateway for FUSE diagnostics. Run
`sandbox exec -n <sandbox-name> -- openrind-shell-fused health` through that CLI
with the managed gateway endpoint. The filesystem state must be `writable`.
`Ready` alone does not prove initialization succeeded. A manual
`sandbox connect` opens a diagnostic shell, not a signed agent launch.

## Persistence and safety

- `/sandbox/work` is PostgreSQL-backed FUSE, not a watched or mirrored folder.
- Claude uses `/sandbox/claude-home`, on a separate persistent named volume.
- One writable sandbox per workspace; do not create a duplicate to resume.
- FUSE daemon exit or lease loss ends the session. Never grant Claude mount
  capabilities, `/dev/fuse`, or a PostgreSQL/TLS-bypass fallback.
- Never delete a sandbox or volume without the user's explicit request.
- Compatibility is a separately requested legacy runtime, not recovery for a
  failed mandatory Haloop launch. Do not reuse its old provider recipe.
- Desktop captures traces only. Export them to the w8-haloop web app for analysis
  and Harbor task generation. Post-start capture is best-effort; a successful
  inference response does not prove its trace was stored.

Attribution

openrindopenrind
View sourceSee grades on GitHubMore from openrind →
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 →