Agent skill

Tinyagi Admin

by TinyAGI in TinyAGI/tinyagi

Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code.

MITAuto-check passedBackend & APIs

Install Tinyagi Admin

skills CLI
$ npx skills add TinyAGI/tinyagi --skill tinyagi-admin -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TinyAGI/tinyagi tinyagi-admin --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TinyAGI/tinyagi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/tinyagi-admin .claude/skills/tinyagi-admin && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tinyagi-admin
GitHub stars
3.6k
Token cost
~2.5k tokens
SKILL.md length
380 words
Files
2 (incl. scripts)
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code.

  • The agent needs to: list/add/remove/update agents
  • SKILL.md covers Important paths, Interactivity warning, REST API (preferred for… and Direct settings.json editing, plus 2 more sections
  • Runs Shell scripts from its folder; calls curl, jq and npm
  • Check queue status

What it does

Tinyagi Admin is an agent skill from TinyAGI/tinyagi. Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code. Use when the agent needs to: list/add/remove/update agents or teams, check queue status, view logs, start/stop/restart TinyAGI, change settings (provider, model, channels), send messages to the queue, manage tasks, retry dead-letter messages, view recent responses, modify TinyAGI source code or configuration, or perform any administrative operation on the TinyAGI platform. Triggers: 'manage…

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/tc-api.sh`).

It sits in Backend & APIs. The repository describes itself as: TinyAGI is the agent teams orchestrator for One Person Company. (fka TinyClaw). The licence is MIT.

When your agent uses it

  • The agent needs to: list/add/remove/update agents
  • Check queue status
  • Start/stop/restart TinyAGI
  • Change settings (provider

Example prompts

  • “manage tinyagi”
  • “add an agent”
  • “remove a team”
  • “/tinyagi-admin”

Requirements

  • A Bash shell
  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit 2db3a03. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • curl
    • jq
    • npm
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, npm and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tinyagi Admin loads about 2.5k tokens when it runs. Until then it costs about 174 tokens; SKILL.md has 380 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~174
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from TinyAGI/tinyagi at commit 2db3a03, republished under its MIT licence (© TinyAGI). 380 words, ~2,545 tokens.

Download SKILL.mdSave it as .claude/skills/tinyagi-admin/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
tinyagi-admin
description
Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code. Use when the agent needs to: list/add/remove/update agents or teams, check queue status, view logs, start/stop/restart TinyAGI, change settings (provider, model, channels), send messages to the queue, manage tasks, retry dead-letter messages, view recent responses, modify TinyAGI source code or configuration, or perform any administrative operation on the TinyAGI platform. Triggers: 'manage tinyagi', 'add an agent', 'remove a team', 'check queue', 'view logs', 'restart tinyagi', 'change provider', 'update settings', 'create a task', 'modify tinyagi code'.

TinyAGI Admin

Operate and manage the TinyAGI multi-agent system. This skill covers both runtime administration (via the REST API) and source code modification.

Important paths

  • TinyAGI home (runtime data): ~/.tinyagi/
    • settings.json — all configuration (agents, teams, channels, models, workspace)
    • tinyagi.db — SQLite queue database
    • tasks.json — Kanban tasks
    • pairing.json — sender allowlist
    • logs/ — queue, daemon, and channel logs
    • chats/ — team chain chat history
    • events/ — real-time event files
    • plugins/ — plugin directory
  • TinyAGI source code: the repo where this skill is installed (check git rev-parse --show-toplevel or look for tinyagi.sh in parent dirs)
  • Agent workspaces: configured in settings.json under workspace.path (default: ~/tinyagi-workspace/{agent_id}/)

Interactivity warning

Many tinyagi CLI commands are interactive (prompt for user input). Do NOT run these directly:

  • tinyagi setup — fully interactive wizard
  • tinyagi agent add — prompts for all fields
  • tinyagi team add — prompts for all fields
  • tinyagi agent remove <id> — prompts [y/N]
  • tinyagi team remove <id> — prompts [y/N]
  • tinyagi team remove-agent <t> <a> — may prompt for new leader + [y/N]

Instead, use the REST API or direct settings.json edits (see below).

Non-interactive CLI commands (safe to run)

These CLI commands accept all parameters as arguments and do not prompt:

bash
tinyagi start                              # Start daemon
tinyagi stop                               # Stop all processes
tinyagi restart                            # Restart daemon
tinyagi status                             # Show status
tinyagi logs [queue|discord|telegram|whatsapp|heartbeat|daemon|all]
tinyagi send "<message>"                   # Send message to default agent
tinyagi send "@agent_id <message>"         # Send to specific agent
tinyagi reset <agent_id> [agent_id...]     # Reset agent conversations
tinyagi provider anthropic                 # Switch global provider
tinyagi provider openai --model gpt-5.3-codex
tinyagi model sonnet                       # Switch global model
tinyagi agent list                         # List agents
tinyagi agent show <id>                    # Show agent config
tinyagi agent provider <id> <provider>     # Set agent provider
tinyagi agent provider <id> <provider> --model <model>
tinyagi team list                          # List teams
tinyagi team show <id>                     # Show team config
tinyagi team add-agent <team_id> <agent_id>  # Add agent to team (no prompts)
tinyagi channel start <channel>            # Start a channel
tinyagi channel stop <channel>             # Stop a channel
tinyagi channel restart <channel>          # Restart a channel
tinyagi channel reset <channel>            # Reset channel auth
tinyagi pairing list                       # Show all pairings
tinyagi pairing pending                    # Show pending
tinyagi pairing approved                   # Show approved
tinyagi pairing approve <code>             # Approve a sender
tinyagi pairing unpair <channel> <sender_id>

REST API (preferred for programmatic operations)

The API server runs on http://localhost:3777 (configurable via TINYAGI_API_PORT). The API server is available when TinyAGI is running.

Agents
bash
# List agents
curl -s http://localhost:3777/api/agents | jq

# Create or update agent (non-interactive, auto-provisions workspace)
curl -s -X PUT http://localhost:3777/api/agents/coder \
  -H 'Content-Type: application/json' \
  -d '{"name":"Coder","provider":"anthropic","model":"sonnet"}'

# Create agent with a system prompt (written to AGENTS.md in workspace on provisioning)
curl -s -X PUT http://localhost:3777/api/agents/coder \
  -H 'Content-Type: application/json' \
  -d '{"name":"Coder","provider":"anthropic","model":"sonnet","system_prompt":"You are a senior engineer. Always write tests."}'

# Optional fields: working_directory, system_prompt, prompt_file

# Delete agent
curl -s -X DELETE http://localhost:3777/api/agents/coder
Teams
bash
# List teams
curl -s http://localhost:3777/api/teams | jq

# Create or update team
curl -s -X PUT http://localhost:3777/api/teams/dev \
  -H 'Content-Type: application/json' \
  -d '{"name":"Dev Team","agents":["coder","reviewer"],"leader_agent":"coder"}'

# Delete team
curl -s -X DELETE http://localhost:3777/api/teams/dev
Settings
bash
# Get full settings
curl -s http://localhost:3777/api/settings | jq

# Update settings (shallow merge)
curl -s -X PUT http://localhost:3777/api/settings \
  -H 'Content-Type: application/json' \
  -d '{"monitoring":{"heartbeat_interval":1800}}'
Services (channels & daemon)
bash
# Start a channel
curl -s -X POST http://localhost:3777/api/services/channel/telegram/start

# Stop a channel
curl -s -X POST http://localhost:3777/api/services/channel/telegram/stop

# Restart a channel
curl -s -X POST http://localhost:3777/api/services/channel/telegram/restart

# Start all enabled channels
curl -s -X POST http://localhost:3777/api/services/apply

# Restart the entire process (exit code 75 triggers restart loop in Docker)
curl -s -X POST http://localhost:3777/api/services/restart
Messages
bash
# Send message to queue (processed by agent)
curl -s -X POST http://localhost:3777/api/message \
  -H 'Content-Type: application/json' \
  -d '{"message":"@coder fix the login bug","sender":"Admin","channel":"api"}'
Queue
bash
# Queue status
curl -s http://localhost:3777/api/queue/status | jq

# Recent responses
curl -s http://localhost:3777/api/responses?limit=10 | jq

# Dead-letter messages
curl -s http://localhost:3777/api/queue/dead | jq

# Retry a dead message
curl -s -X POST http://localhost:3777/api/queue/dead/123/retry

# Delete a dead message
curl -s -X DELETE http://localhost:3777/api/queue/dead/123
Tasks
bash
# List tasks
curl -s http://localhost:3777/api/tasks | jq

# Create task
curl -s -X POST http://localhost:3777/api/tasks \
  -H 'Content-Type: application/json' \
  -d '{"title":"Fix auth bug","description":"Login fails on mobile","status":"backlog","assignee":"coder","assigneeType":"agent"}'

# Update task
curl -s -X PUT http://localhost:3777/api/tasks/TASK_ID \
  -H 'Content-Type: application/json' \
  -d '{"status":"in-progress"}'

# Delete task
curl -s -X DELETE http://localhost:3777/api/tasks/TASK_ID
Logs
bash
# Recent queue logs
curl -s http://localhost:3777/api/logs?limit=50 | jq
Show full SKILL.md (162 more words)Show less

Direct settings.json editing

When the API server is not running, edit ~/.tinyagi/settings.json directly. Use jq for safe atomic edits:

bash
SETTINGS="$HOME/.tinyagi/settings.json"

# Add an agent
jq --arg id "analyst" --argjson agent '{"name":"Analyst","provider":"anthropic","model":"sonnet","working_directory":"'$HOME'/tinyagi-workspace/analyst"}' \
  '.agents[$id] = $agent' "$SETTINGS" > "$SETTINGS.tmp" && mv "$SETTINGS.tmp" "$SETTINGS"

# Remove an agent
jq 'del(.agents["analyst"])' "$SETTINGS" > "$SETTINGS.tmp" && mv "$SETTINGS.tmp" "$SETTINGS"

# Add a team
jq --arg id "research" --argjson team '{"name":"Research Team","agents":["analyst","writer"],"leader_agent":"analyst"}' \
  '.teams //= {} | .teams[$id] = $team' "$SETTINGS" > "$SETTINGS.tmp" && mv "$SETTINGS.tmp" "$SETTINGS"

After editing settings.json, run tinyagi restart to pick up changes.

Modifying TinyAGI source code

When modifying TinyAGI's own code (features, bug fixes, new routes, etc.):

  • Monorepo packages:
    • packages/core/src/ — shared utilities (config, db, logging, types, plugins, agent invocation)
    • packages/server/src/ — API server (Hono framework)
    • packages/server/src/routes/ — route handlers (agents, teams, settings, queue, tasks, messages, logs, services)
    • packages/main/src/ — entry point, queue processor, channel/heartbeat lifecycle
    • packages/cli/src/ — CLI modules (daemon, channel, install, logs, agent, team, provider, etc.)
    • packages/cli/bin/tinyagi.mjs — thin CLI dispatcher (delegates to compiled modules in dist/)
    • packages/teams/src/ — team orchestration
    • packages/visualizer/src/ — TUI dashboards (team visualizer, chatroom viewer)
  • Skills: .agents/skills/ — skill definitions (copied to agent workspaces on provision)
  • Web portal: tinyoffice/ — Next.js app
  • Docker: Dockerfile, docker-entrypoint.sh, docker-compose.yml

After modifying TypeScript source, rebuild:

bash
cd <tinyagi-repo> && npm run build

Then restart the daemon to load changes:

bash
tinyagi restart

Workflow examples

Add a new agent and assign to a team
bash
# 1. Create agent via API
curl -s -X PUT http://localhost:3777/api/agents/reviewer \
  -H 'Content-Type: application/json' \
  -d '{"name":"Code Reviewer","provider":"anthropic","model":"sonnet"}'

# 2. Add to existing team (non-interactive CLI)
tinyagi team add-agent dev reviewer
Check system health
bash
tinyagi status
curl -s http://localhost:3777/api/queue/status | jq
curl -s http://localhost:3777/api/queue/dead | jq
tinyagi logs queue
Create a task and assign to agent
bash
curl -s -X POST http://localhost:3777/api/tasks \
  -H 'Content-Type: application/json' \
  -d '{"title":"Review PR #42","status":"backlog","assignee":"reviewer","assigneeType":"agent"}'

© TinyAGI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in .agents/skills/tinyagi-admin of TinyAGI/tinyagi.

  • SKILL.md
  • scripts/tc-api.sh

Open the folder on GitHubat commit 2db3a03

Compare with similar skills

Tinyagi Admin next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tinyagi Admin compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tinyagi Admin this skillTinyAGI/tinyagi3.6k—~2.5kAutomated safety check: PassMIT
Configuring Horizoncoollabsio/coolify63k4 repos~898Automated safety check: PassMIT
Nestjs Best Practicesrolling-scopes/rsschool-app10k6 repos~1.2kAutomated safety check: PassMIT
Sub2API AdminWei-Shaw/sub2api43k1 repos~717Automated safety check: PassLGPL-3.0
Firecrawl Build Onboardingfirecrawl/firecrawl189k1 repos~1.4kAutomated safety check: NotesISC
Obsidian BasesAtmosphere/atmosphere3.8k22 repos~3.2kAutomated safety check: PassApache-2.0

Similar skills

  • Configuring Horizon

    coollabsio/coolify

    A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.

    63k GitHub starsUsed in 4 repos~898 tokens
    Backend & APIsAuto-check passed
  • Nestjs Best Practices

    rolling-scopes/rsschool-app

    NestJS best practices and architecture patterns for building production-ready applications.

    10k GitHub starsUsed in 6 repos~1.2k tokens
    Backend & APIsAuto-check passed
  • Sub2API Admin

    Wei-Shaw/sub2api

    Manages a Sub2API deployment from the command line: accounts, redeem and invitation codes, groups, proxies, imports, exports and raw admin API calls.

    43k GitHub starsUsed in 1 repo~717 tokens
    Backend & APIsAuto-check passed
  • Firecrawl Build Onboarding

    firecrawl/firecrawl

    Gets Firecrawl working in a project: signs you in through the browser, saves FIRECRAWL_API_KEY to .env and picks the first SDK or REST path.

    189k GitHub starsUsed in 1 repo~1.4k tokens
    Backend & APIsAuto-check: notes
  • Obsidian Bases

    Atmosphere/atmosphere

    Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries.

    3.8k GitHub starsUsed in 22 repos~3.2k tokens
    Backend & APIsAuto-check passed
  • Fortify Development

    coollabsio/coolify

    ACTIVATE when the user works on authentication in Laravel. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 4 repos~1.9k tokens
    Backend & APIsAuto-check passed

More from TinyAGI/tinyagi

  • Schedule

    TinyAGI/tinyagi

    Create, list, and delete scheduled tasks (recurring or one-time) that send messages to agents.

    3.6k GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Send User Message

    TinyAGI/tinyagi

    Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp).

    3.6k GitHub stars~829 tokensUpdated 6 mo ago
    Auto-check passed
  • Skills Manager

    TinyAGI/tinyagi

    Search for and install skills from the skills registry to agent workspaces.

    3.6k GitHub stars~528 tokensUpdated 6 mo ago
    Auto-check passed
  • Tasks

    TinyAGI/tinyagi

    Manage your assigned tasks on the TinyAGI kanban board — list tasks, update task status, create new tasks, and add or view comments.

    3.6k GitHub stars~721 tokensUpdated 6 mo ago
    Auto-check passed
  • Memory

    TinyAGI/tinyagi

    Manage your persistent hierarchical memory — save, update, search, and organize knowledge as markdown files in the memory/ folder.

    3.6k GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Tinyagi Admin

What does Tinyagi Admin do?

Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code. Tinyagi Admin is an agent skill from TinyAGI/tinyagi. Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code.

When should I use Tinyagi Admin?

Tinyagi Admin fits situations like: the agent needs to: list/add/remove/update agents; check queue status; start/stop/restart TinyAGI; change settings (provider.

How do I install Tinyagi Admin in Claude Code?

Run `npx skills add TinyAGI/tinyagi --skill tinyagi-admin -a claude-code`. Or copy the skill folder (.agents/skills/tinyagi-admin in TinyAGI/tinyagi) into .claude/skills/tinyagi-admin in your project. Claude Code loads it when a task matches its description.

How do I install Tinyagi Admin in Codex?

Run `npx skills add TinyAGI/tinyagi --skill tinyagi-admin -a codex`. Or copy the skill folder (.agents/skills/tinyagi-admin in TinyAGI/tinyagi) into .agents/skills/tinyagi-admin in your project. Codex loads it when a task matches its description.

Can I use Tinyagi Admin in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TinyAGI/tinyagi --skill tinyagi-admin -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tinyagi-admin, .gemini/skills/tinyagi-admin, .github/skills/tinyagi-admin and .opencode/skills/tinyagi-admin in your project.

What does Tinyagi Admin need to run?

Going by SKILL.md and its folder, Tinyagi Admin needs a shell for the scripts in its folder and the command-line tools its instructions call (curl, jq, npm and git). Our summary lists: A Bash shell; Docker.

Does Tinyagi Admin access the network?

SKILL.md contains no URLs. Its commands use curl, npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Tinyagi Admin safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Tinyagi Admin use?

Tinyagi Admin is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tinyagi Admin use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Tinyagi Admin?

Skills that share tags, products or a category with Tinyagi Admin: Configuring Horizon (coollabsio/coolify, 63k stars), Nestjs Best Practices (rolling-scopes/rsschool-app, 10k stars), Sub2API Admin (Wei-Shaw/sub2api, 43k stars) and Firecrawl Build Onboarding (firecrawl/firecrawl, 189k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tinyagi Admin?

TinyAGI (a GitHub organization) maintains it in TinyAGI/tinyagi, which has 3,620 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on March 30, 2026.

Source: TinyAGI/tinyagi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.