What makes Tandoor Recipe CLI notable?

1.3K downloads. Trust evidence available

How should Tandoor Recipe CLI be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Tandoor Recipe CLI

Manage recipes, meal plans, and shopping lists on a Tandoor Recipe Manager instance via CLI.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

1.5.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 1.5.0release · observed May 18, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s174qsh3740skgwa1m8x5xsgpd8641p7:tandoor-cli

Install using `clawhub skill install s174qsh3740skgwa1m8x5xsgpd8641p7:tandoor-cli` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/dcenatiempo/tandoor-cli before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-dcenatiempo-tandoor-cli/snapshot"

Documentation

CLAWHUB

146,290 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: tandoor-recipe-cli
description: Manage recipes, meal plans, and shopping lists on a Tandoor Recipe Manager instance via CLI.
version: 1.5.0
compatibility: ">=18"
license: MIT
metadata:
  author: dcenatiempo
  repository: https://github.com/dcenatiempo/tandoor-cli
---

## Tandoor CLI Skill

This skill provides AI agents with the ability to interact with a Tandoor Recipe Manager instance using the `tandoor-cli` command-line tool.

### Prerequisites

The `tandoor-cli` tool must be installed and configured.

**Version Compatibility:** This skill documentation corresponds to the version specified in the metadata above. Before using this skill:
1. Verify your installed CLI version: `tandoor -V`
2. Ensure the installed version matches the skill version to avoid unexpected behavior or missing commands
3. If versions don't match, reinstall the CLI tool following the setup instructions in `references/SETUP.md`

If `tandoor -V` produces no valid version, see the setup instructions in `references/SETUP.md`.

### Security & Permission Model

**⚠️ IMPORTANT: This skill provides mutation authority over your Tandoor instance.**

- **Read operations** (list, search, get, random) are safe and require no confirmation
- **Write operations** (add, update, import) modify data but are typically reversible
- **Destructive operations** (delete, clear, household management) require explicit user approval before execution
- **Bulk operations** (shopping check --all, clear) affect multiple items and require confirmation
- **Administrative operations** (household management, user assignment, invite creation) require privileged credentials and explicit approval

**Token Security:**
- Use the **least-privileged token** possible for your use case
- Prefer read-only tokens if you only need to query recipes
- Avoid using space-owner or admin tokens unless household management is required
- Consider short-lived tokens (days/weeks) instead of long-lived tokens (years)
- Store tokens securely and rotate them regularly
- Revoke tokens immediately if compromised or no longer needed

**Supply Chain:**
- This skill uses the `tandoor-cli` npm package
- Verify the package source before first use: https://www.npmjs.com/package/tandoor-cli
- Review the package repository: https://github.com/dcenatiempo/tandoor-cli
- **Recommended:** Pin to the specific version matching this skill (see version in metadata above) to avoid unexpected updates
- Install pinned version: `npm install -g tandoor-cli@<version>` (replace `<version>` with the skill version)

### Invocation

```bash
tandoor <command> [options]
```

### Output formats and deprecated flags

Commands that print data accept **`--format text|json|api`** (default: `text`):

| `--format` | Use for |
|------------|---------|
| `text` | Human-readable output (default) |
| `json` | Slim JSON where supported (recipe add/update shape + `id` on `get`, `list`, `search`, `random`) |
| `api` | Raw Tandoor API JSON |

**Deprecated (output):**

_meta.json

{
  "ownerId": "kn7d75mc2rzjgptnfjg8382my9864gnx",
  "slug": "tandoor-cli",
  "version": "1.5.0",
  "publishedAt": 1779130756604
}

references/SETUP.md

# tandoor-cli Setup Guide

A command-line interface for [Tandoor Recipe Manager](https://tandoor.dev).

---

## Prerequisites

- Node.js 18+
- npm 8+
- A running Tandoor instance (local or remote)

---

## Installation

### Option 1: Install globally via npm

```bash
npm install -g tandoor-cli
```

After the global install, the `tandoor` command becomes available system-wide.

### Option 2: Run without installing

```bash
npx tandoor-cli <command>
```

No global install is required. `npx` downloads and runs the CLI on demand.

**Note:** The rest of this documentation assumes a global install.

---

## Configuration

`TANDOOR_URL` and at least one authentication method are required.

The CLI supports three configuration sources, applied in this order (highest priority first):

1. Environment variables
2. Persistent config file
3. `.env` file

### Option 1: Environment variables

```bash
export TANDOOR_URL=http://localhost:8080
export TANDOOR_API_TOKEN=your_token_here
```

Environment variables take precedence over stored config and `.env` settings.

### Option 2: `tandoor configure`

Run the interactive setup command to save credentials to `~/.config/tandoor-cli/config.json`:

```bash
# without install
npx tandoor-cli configure

# with global install
tandoor configure
```

You will be prompted for:
- `TANDOOR_URL`
- `TANDOOR_API_TOKEN`

The file is written with restricted permissions (0600) to protect your credentials.

### Option 3: `.env` file

Create a `.env` file in your working directory:

```dotenv
TANDOOR_URL=http://localhost:8080
TANDOOR_API_TOKEN=your_token_here
TANDOOR_USERNAME=
TANDOOR_PASSWORD=
```

The CLI loads `.env` automatically when present.

---

## Authentication

### API token (preferred)

Use an OAuth2 access token with Bearer authentication. 

**Important:** The regular DRF token shown in Tandoor's Settings → API does **not** work for this CLI. You need an OAuth2 access token.

**⚠️ Security Note:** Use the shortest token lifetime appropriate for your use case. For AI agent use, consider tokens that expire in days or weeks, not years.

#### Generating an OAuth2 token

If you're running Tandoor in Docker, you can generate an OAuth2 token using the Django shell. Choose the appropriate example based on your needs:

##### Read-Only Token (Safest)

For querying recipes only:

```bash
docker exec <your-container-name> /opt/recipes/venv/bin/python /opt/recipes/manage.py shell -c "
from oauth2_provider.models import Application, AccessToken
from django.contrib.auth.models import User
from django.utils import timezone
from datetime import timedelta
import secrets

user = User.objects.get(username='YOUR_USERNAME')

app, _ = Application.objects.get_or_create(
    name='tandoor-cli',
    defaults=dict(
        user=user,
        client_type=Application.CLIENT_CONFIDENTIAL,
        authorization_grant_type=Application.GRANT_PASSWORD,
    )
)

token = AccessToken.objects.create(
    user=user,
    application=app,
    token=secrets.token_

SECURITY_REVIEW_RESPONSE.md

# Response to OlawHub Security Review

This document summarizes the changes made to address security concerns raised in the OlawHub skill review.

## Review Date
May 4, 2026

## Summary of Changes

All security concerns have been addressed through documentation updates, explicit approval gates, and security best practices guidance.

---

## 1. Tool Misuse and Exploitation (HIGH SEVERITY)

### Original Concern
> The skill exposes destructive, bulk, and account-administration operations to the agent, but the instructions do not add explicit approval gates or limits for these high-impact actions.

### Resolution

**Files Modified:**
- `SKILL.md`
- `references/SETUP.md`

**Changes Made:**

1. **Command Classification System**
- All commands now categorized by risk level:
- Read operations (safe, no approval)
- Write operations (require user confirmation)
- Destructive operations (require explicit confirmation)
- Administrative operations (require privileged token + explicit confirmation)

2. **Explicit Approval Gates**
- Added "Approval Required" column to command tables
- Documented specific confirmation messages for each destructive operation
- Examples:
- `delete <id>`: "This will permanently delete recipe X. Cannot be undone. Confirm?"
- `shopping check --all`: "This will mark ALL shopping items as checked. Confirm?"
- `household users assign`: "This will move user X to household Y. Confirm?"

3. **Agent Behavior Rules Section**
- Clear instructions on when to proceed vs. when to ask
- Explicit prohibition on using `--force` without user instruction
- Requirement to explain impact before destructive operations

4. **Security Warning Banner**
- Added prominent warning at top of SKILL.md
- States: "This skill provides mutation authority over your Tandoor instance"
- Directs users to only install if they want agent mutation authority

**User Impact:** Agents can no longer execute destructive operations without explicit user approval. Users maintain full control over high-impact actions.

---

## 2. Agentic Supply Chain Vulnerabilities (LOW SEVERITY)

### Original Concern
> The skill relies on an external npm package that is not included in the reviewed artifact set; npx may download and run package code on demand.

### Resolution

**Files Modified:**
- `SKILL.md`
- `SECURITY.md`

**Changes Made:**

1. **Version Awareness**
- Documentation acknowledges the npm package dependency
- Recommends version pinning for production use

2. **Verification Links**
- Added direct links to npm package: https://www.npmjs.com/package/tandoor-cli
- Added direct link to source repository: https://github.com/dcenatiempo/tandoor-cli
- Included in "Before first use" checklist

3. **Pre-Installation Checklist**
- Verify the npm package
- Review the source code
- Consider using a test instance first

4. **Supply Chain Security Section**
- Added to SKILL.md under "Security & Permissi

SECURITY.md

# Security Guidelines for Tandoor CLI Skill

This document addresses security concerns and best practices for using the tandoor-cli skill with AI agents.

## Overview

The tandoor-cli skill provides programmatic access to your Tandoor Recipe Manager instance. Like any tool with write access to your data, it requires careful configuration and usage to maintain security.

## Addressed Security Concerns

### 1. Tool Misuse and Exploitation (HIGH SEVERITY)

**Concern:** The skill exposes destructive, bulk, and account-administration operations without explicit approval gates.

**Mitigation:**
- **Command Classification:** All commands are now classified by risk level (read, write, destructive, administrative)
- **Approval Gates:** The SKILL.md explicitly requires user confirmation before:
  - Any write operation (add, update, import)
  - Any destructive operation (delete, clear, bulk operations)
  - Any administrative operation (household management, user assignment)
- **Agent Behavior Rules:** Clear instructions prevent agents from executing high-risk commands without explicit user approval
- **No Automatic --force:** Agents are forbidden from using `--force` flags without explicit user instruction

**User Action Required:**
- Review the command classification table in SKILL.md
- Only install this skill if you want the agent to have mutation authority
- Monitor agent behavior and revoke access if misuse is detected

### 2. Agentic Supply Chain Vulnerabilities (LOW SEVERITY)

**Concern:** The skill relies on an external npm package that could be compromised.

**Mitigation:**
- **Version Pinning:** The skill explicitly uses `npx [email protected]` to pin to a known version
- **Verification Links:** SKILL.md provides direct links to:
  - npm package: https://www.npmjs.com/package/tandoor-cli
  - Source repository: https://github.com/dcenatiempo/tandoor-cli
- **Pre-Installation Checklist:** Users are instructed to verify the package before first use
- **No Auto-Updates:** Using `@version` syntax prevents automatic updates to potentially compromised versions

**User Action Required:**
- Verify the npm package and repository before first installation
- Review the package source code if using privileged credentials
- Monitor npm security advisories for the tandoor-cli package
- Update to newer versions only after reviewing changelogs

### 3. Identity and Privilege Abuse - Space Owner Token (HIGH SEVERITY)

**Concern:** The skill directs use of a highly privileged space-owner token for household invite management.

**Mitigation:**
- **Least Privilege Principle:** SKILL.md now emphasizes using the least-privileged token possible
- **Token Scoping Guidance:**
  - Read-only tokens for query operations
  - Standard user tokens for recipe management
  - Admin tokens only when household management is required
  - Space-owner tokens only for invite link creation
- **Explicit Warnings:** Administrative commands clearly state they require privileged tokens
- **Permi

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.