cosin

Use this skill when an agent needs to operate the `cosin` CLI from the terminal. `cosin` accepts only relative paths, lists available skills through the `skills` subcommand, can call COS API paths directly, and can call `/cos/...` skills by turning them into x402 pay-and-call requests to the COS backend. This skill is for using the CLI, not for editing the cosin source code.

3,891 stars
Complexity: easy

About this skill

The `cosin` skill provides AI agents with the capability to seamlessly interface with the `cosin` CLI, a terminal tool designed for interacting with the COS API and associated skills. This skill automates the process of making various types of requests, including direct calls to `https://skills.bankofuniverse.org/skills`, standard COS API paths like `/v1/me`, and special `/cos/...` skill paths that are internally converted into x402 pay-and-call requests to a COS backend. It strictly enforces the use of relative paths for all operations, streamlining command execution. Agents can leverage this skill to programmatically perform operations such as querying available skills, retrieving user information, or executing advanced, token-gated skill calls that involve payment mechanisms. The skill ensures secure handling of sensitive bearer tokens, advising against hardcoding and promoting their treatment as command-line arguments. By abstracting the complexities of `cosin`'s syntax and request types, this skill allows AI agents to focus on the desired outcome rather than the intricacies of CLI operation. This skill is particularly useful for agents that need to automate interactions with the COS ecosystem, enabling them to fetch data, trigger actions, or integrate with other services hosted on the COS platform. It serves as a bridge, transforming agent prompts into executable `cosin` commands, complete with proper authentication and request formatting, making it an essential tool for automating tasks within this specific environment.

Best use case

The primary use case is for AI agents that need to programmatically interact with the COS API or execute specific COS-backed skills from a terminal environment. Developers and power users building automated workflows, monitoring systems, or integrating external services with the COS ecosystem would benefit most by allowing their AI agents to securely and efficiently operate the `cosin` CLI without direct human intervention.

Use this skill when an agent needs to operate the `cosin` CLI from the terminal. `cosin` accepts only relative paths, lists available skills through the `skills` subcommand, can call COS API paths directly, and can call `/cos/...` skills by turning them into x402 pay-and-call requests to the COS backend. This skill is for using the CLI, not for editing the cosin source code.

The agent will successfully execute `cosin` commands, receiving the requested data or confirmation of action from the COS API or a COS-backed skill, without exposing sensitive credentials.

Practical example

Example input

Using the `cosin` CLI, retrieve my user profile from the COS API. My token is `abc123def456`. Then, list all available skills.

Example output

# First request output
{
  "id": "user123",
  "username": "agent_user",
  "email": "agent@example.com",
  "roles": ["developer", "agent"]
}

# Second request output (partial)
[
  {"name": "skill-a", "description": "Description of skill A"},
  {"name": "skill-b", "description": "Description of skill B"},
  ...
]

When to use this skill

  • An AI agent needs to call the COS API for data retrieval or state modification.
  • An AI agent needs to invoke a `/cos/...` skill that requires an x402 pay-and-call request.
  • An AI agent needs to list available skills from `https://skills.bankofuniverse.org`.
  • Automating interactions with the COS ecosystem from a command-line interface.

When not to use this skill

  • The task does not involve interacting with the `cosin` CLI or the COS API/skills.
  • The user intends to edit the `cosin` source code rather than use the CLI.
  • Absolute URLs are required for requests (as `cosin` only accepts relative paths).
  • Sensitive data other than the bearer token needs protection, which `cosin` might not explicitly handle beyond its `--key` flag.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/cosin/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/0xcipher0/cosin/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/cosin/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How cosin Compares

Feature / AgentcosinStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityeasyN/A

Frequently Asked Questions

What does this skill do?

Use this skill when an agent needs to operate the `cosin` CLI from the terminal. `cosin` accepts only relative paths, lists available skills through the `skills` subcommand, can call COS API paths directly, and can call `/cos/...` skills by turning them into x402 pay-and-call requests to the COS backend. This skill is for using the CLI, not for editing the cosin source code.

How difficult is it to install?

The installation complexity is rated as easy. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Cosin CLI

Use `cosin` to call the COS API and COS-backed skills from the terminal.

## What the CLI does

`cosin` now accepts only relative paths.

There are three request styles:

1. `skills`
   Calls `https://skills.bankofuniverse.org/skills` directly and prints the upstream body directly.

2. Normal COS API paths such as `/v1/me`
   These are sent directly to the COS API host.

3. Skill paths under `/cos/...`
   These are converted internally into x402 pay-and-call requests:
- keeps the same request path
- builds the target URL from `SKILLS_BASE_URL`
- sends that target URL to `POST /agent/pay-and-call` on the COS API host

Users should not pass absolute URLs to the CLI anymore.

## Gather inputs

Collect these inputs before running the CLI:

- A COS bearer token for `--key`
- An HTTP method
- A relative path starting with `/`
- Optional JSON for `--json`
- Optional repeatable headers for `--header` or `-H`
- Optional `--base-url` override for normal COS API calls

Ask for the token if the user has not provided one. Treat it as sensitive.

## Protect credentials

- Treat the `--key` value as sensitive
- Do not print, commit, or hardcode the token
- Keep the token in the command line argument, not in repo files

## Run the CLI

Use one of these command shapes:

```sh
cosin --key <token> <METHOD> <PATH> [--json '<json>'] [--header 'Name: value'] [--base-url <url>]
cosin --key <token> agent [status|me] [--base-url <url>]
cosin --key <token> skills
```

Important flags:

- `--key <token>` for the required bearer token
- `--json <json>` for an optional JSON request body
- `--header 'Name: value'` or `-H 'Name: value'` for repeatable custom headers
- `--base-url <url>` to override the default COS API base URL for direct API calls
- `--version` or `-v` to print the installed CLI version
- `--help` or `-h` to print usage

Subcommand notes:

- `skills` does not accept `--json`
- `skills` does not accept custom headers
- `agent` does not accept `--json`
- `agent` does not accept custom headers

## Supported paths

### Built-in catalog

Use this to discover available skills:

```sh
cosin --key <token> skills
```

Expected upstream skills include:

- `/cos/crypto/chainlink/random`
  Returns a random value from the Chainlink-based skill endpoint.
- `/cos/crypto/price/:symbol`
  Returns the latest price for a supported token symbol.

Supported symbols for `/cos/crypto/price/:symbol`:

- `BTC`
- `ETH`
- `HYPE`
- `SOL`
- `TRX`
- `USDT`
- `USDC`

### Direct COS API calls

Use normal API paths to call COS directly:

```sh
cosin --key <token> GET /v1/me
cosin --key <token> POST /v1/orders --json '{"symbol":"BTCUSDT"}'
```

### Skill calls through `/cos/...`

Use `/cos/...` when you want to call a skill through COS:

```sh
cosin --key <token> GET /cos/crypto/chainlink/random
cosin --key <token> GET /cos/crypto/price/BTC
```

Internally, the CLI turns those into x402 pay-and-call requests to the COS backend.

## Use the agent shortcut

Use `agent`, `agent status`, or `agent me` as a convenience alias for `GET /agent/me`.

```sh
cosin --key <token> agent
cosin --key <token> agent status
cosin --key <token> agent me
```

Do not combine `agent` with `--json` or custom headers.

## Validate inputs before running

- Ensure the path starts with `/`
- Do not pass absolute URLs
- Use `skills`, not `GET /skills`
- Ensure `--json` is valid JSON
- Ensure headers use `Name: value`
- For `/cos/crypto/chainlink/random`, only use `GET`
- For `/cos/crypto/price/:symbol`, only use `GET` and only the supported symbols

## Read the output

Expect the CLI to:

- Print an HTTP status line for normal API requests, `/cos/...` skill calls, and `agent`
- Print only the upstream body for the `skills` subcommand
- Pretty-print JSON response bodies
- Print `<empty response body>` for empty responses
- Return a non-zero exit code for unsuccessful HTTP responses or CLI argument errors

## Work locally in this repo

Use the local build when working inside this repository:

```sh
bun run build
./dist/index.js --key <token> agent
./dist/index.js --key <token> skills
./dist/index.js --key <token> GET /v1/me
./dist/index.js --key <token> GET /cos/crypto/chainlink/random
```

Use the published command shape locally when that is more convenient:

```sh
bun x cosin --key <token> agent
bun x cosin --key <token> skills
bun x cosin --key <token> GET /v1/me
bun x cosin --key <token> GET /cos/crypto/price/BTC
```

Related Skills

HIPAA Compliance for AI Agents

3891
from openclaw/skills

Generate HIPAA compliance checklists, risk assessments, and audit frameworks for healthcare organizations deploying AI agents.

Security

Data Governance Framework

3891
from openclaw/skills

Assess, score, and remediate your organization's data governance posture across 6 domains.

Security

Cybersecurity Risk Assessment

3891
from openclaw/skills

You are a cybersecurity risk assessment specialist. When the user needs a security audit, threat assessment, or compliance review, follow this framework.

Security

afrexai-cybersecurity-engine

3891
from openclaw/skills

Complete cybersecurity assessment, threat modeling, and hardening system. Use when conducting security audits, threat modeling, penetration testing, incident response, or building security programs from scratch. Works with any stack — zero external dependencies.

Security

Compliance & Audit Readiness Engine

3891
from openclaw/skills

Your AI compliance officer. Guides startups and scale-ups through SOC 2, ISO 27001, GDPR, HIPAA, and PCI DSS — from zero to audit-ready. No consultants needed.

Security

Compliance Audit Generator

3891
from openclaw/skills

Run internal compliance audits against major frameworks without hiring a consultant.

Security

AI Safety Audit

3891
from openclaw/skills

Comprehensive AI safety and alignment audit framework for businesses deploying AI agents. Built around the UK AI Security Institute Alignment Project standards (2026), EU AI Act requirements, and NIST AI RMF.

Security

clickhouse-github-forensics

3891
from openclaw/skills

Query GitHub event data via ClickHouse for supply chain investigations, actor profiling, and anomaly detection. Use when investigating GitHub-based attacks, tracking repository activity, analyzing actor behavior patterns, detecting tag/release tampering, or reconstructing incident timelines from public GitHub data. Triggers on GitHub supply chain attacks, repo compromise investigations, actor attribution, tag poisoning, or "query github events".

Security

security-guardian

3891
from openclaw/skills

Automated security auditing for OpenClaw projects. Scans for hardcoded secrets (API keys, tokens) and container vulnerabilities (CVEs) using Trivy. Provides structured reports to help maintain a clean and secure codebase.

Security

mema-vault

3891
from openclaw/skills

Secure credential manager using AES-256 (Fernet) encryption. Stores, retrieves, and rotates secrets using a mandatory Master Key. Use for managing API keys, database credentials, and other sensitive tokens.

Security

guardian-wall

3891
from openclaw/skills

Mitigate prompt injection attacks, especially indirect ones from external web content or files. Use this skill when processing untrusted text from the internet, user-uploaded files, or any external source to sanitize content and detect malicious instructions (e.g., "ignore previous instructions", "system override").

Security

SX-security-audit

3891
from openclaw/skills

全方位安全审计技能。检查文件权限、环境变量、依赖漏洞、配置文件、网络端口、Git 安全、Shell 安全、macOS 安全、密钥检测等。支持 CLI 参数、JSON 输出、配置文件。当用户要求"安全检查"、"漏洞扫描"、"权限检查"、"安全审计"时使用此技能。

Security