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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Read Only Mastodon Timeline Cli

ASecurity

Read-only Mastodon CLI. Outputs human-readable timeline summaries or raw JSON.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashgitapisecurityperformance

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill read-only-mastodon-timeline-cli --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Read Only Mastodon Timeline Cli?

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

Security grade badge for Read Only Mastodon Timeline Cli
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-read-only-mastodon-timeline-cli/badge)](https://www.skillsdirectory.com/skills/rondoflow-read-only-mastodon-timeline-cli)

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

Download with Pro
Files
SKILL.md
---
name: read-only-mastodon-timeline-cli
description: "Read-only Mastodon CLI. Outputs human-readable timeline summaries or raw JSON."
category: "Communication"
author: community
version: "1.0.3"
icon: message-circle
---

# Mastodon Scout

## Purpose

Read-only Mastodon CLI that fetches data from the Mastodon API. Returns human-readable summaries by default, or raw JSON with `--json` flag.

---

## Invocation Rules (MANDATORY)

### Binary Selection
- **macOS / Darwin** → `dist/mastodon-scout`
- **Linux** → `dist/mastodon-scout-linux`

### Commands

#### Home Timeline
```
{baseDir}/bin/mastodon-scout home
```
Fetches the authenticated user's home timeline.

#### User Tweets
```
{baseDir}/bin/mastodon-scout user-tweets
```
Fetches the authenticated user's own posts.

#### Mentions
```
{baseDir}/bin/mastodon-scout mentions
```
Fetches mentions of the authenticated user.

#### Search
```
{baseDir}/bin/mastodon-scout search <query>
```
Searches for posts matching the query.

### Flags (Optional)
```
--instance <url>       # Mastodon instance URL (default: https://mastodon.social)
--limit <int>          # Number of items to return (default: 20)
--timeout <int>        # Timeout in seconds (default: 30)
--json                 # Output raw JSON instead of human-readable text
```

### Environment Variables (REQUIRED)
```
MASTODON_TOKEN         # OAuth bearer token for authentication
```

---

## Output Modes

### Text Mode (Default)
```bash
mastodon-scout home
```
Returns human-readable summary of timeline data.

The agent MAY summarize and explain the timeline results to make them more accessible to the user.

### JSON Mode
```bash
mastodon-scout --json home
```
Returns raw JSON data from the Mastodon API.

When JSON mode is used, return the output verbatim without interpretation.

---

## Error Handling

- If the binary exits non-zero:
  - In JSON mode: return error output verbatim
  - In text mode: the agent MAY explain the error to the user
  - Do not retry

- If MASTODON_TOKEN is not set:
  - The binary will exit with an error message
  - Agent should guide the user to the authentication setup section

---

## Examples That Trigger This Skill

- `mastodon-scout home`
- `show my mastodon timeline`
- `check mastodon mentions`
- `search mastodon for "golang"`
- `get my mastodon posts`

---

## Performance Requirements

- Execute binary directly
- No web searches
- No secondary tools beyond the binary
- Minimize latency

---

## Notes

- In text mode: agent MAY summarize and explain results
- In JSON mode: output verbatim, no interpretation
- This skill is **read-only** (no posting, following, or other mutations)

---

## Authentication Setup (Agent MAY Help)

**EXCEPTION TO STRICT MODE**: If the user needs help obtaining a token, the agent **may** provide guidance before executing the skill.

The tool requires a Mastodon OAuth bearer token set in the `MASTODON_TOKEN` environment variable.

### How to Obtain a Token (Guide the User):

**Step 1: Access Development Settings**
- User should log into their Mastodon instance (e.g., mastodon.social, fosstodon.org)
- Navigate to: **Settings → Development** (or Preferences → Development)
- Direct URL format: `https://[instance-domain]/settings/applications`

**Step 2: Create Application**
- Click "New Application"
- Fill in details:
  - **Application name**: `mastodon-scout` (or any name)
  - **Application website**: Can leave blank or use any URL
  - **Redirect URI**: `urn:ietf:wg:oauth:2.0:oob` (for CLI apps)
  - **Scopes**: **CRITICAL - Only select `read`** (uncheck write, follow, push)

**Step 3: Get Access Token**
- Click "Submit"
- Click on the created application to view details
- Copy the **"Your access token"** field value

**Step 4: Set Environment Variable**
```bash
export MASTODON_TOKEN="paste_token_here"
```

**Step 5: Verify Token Works**
```bash
./dist/mastodon-scout home
```

### Common Mastodon Instances:
- `mastodon.social` - General purpose (default)
- `fosstodon.org` - FOSS/tech community
- `mas.to` - Tech focused
- `hachyderm.io` - Tech/infosec community

Use `--instance https://your-instance.com` flag for non-default instances.

### Security Notes to Communicate:
- Token is **read-only** (cannot post, follow, or delete)
- Keep token secret (don't commit to git)
- Can be revoked anytime in Development settings
- Each Mastodon instance requires its own token

---

## Output Format

### Text Mode (Default)
Human-readable summary of posts, formatted for readability. The agent decides how to present the information.

### JSON Mode (`--json` flag)
All commands return JSON in the following format:

```json
{
  "success": true,
  "data": [ /* Mastodon API response */ ]
}
```

Or on error:

```json
{
  "success": false,
  "error": "error message"
}
```

The `data` field contains the raw Mastodon API response without any modifications.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

693621 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →