Agent skill

Agents

by butterbase-ai in butterbase-ai/butterbase-skills

A skill your agent uses when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits.

MITAuto-check passedAgent Workflows

Install Agents

skills CLI

$ npx skills add butterbase-ai/butterbase-skills --skill agents -a claude-code

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

GitHub CLI

$ gh skill install butterbase-ai/butterbase-skills agents --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/butterbase-ai/butterbase-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agents .claude/skills/agents && 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/

Paste into Claude Code

Install the "agents" agent skill from https://github.com/butterbase-ai/butterbase-skills/tree/main/skills/agents into .claude/skills/agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/butterbase-ai/butterbase-skills/tree/main/skills/agents

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add butterbase-ai/butterbase-skills --skill agents -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install butterbase-ai/butterbase-skills agents --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/butterbase-ai/butterbase-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agents .agents/skills/agents && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "agents" agent skill from https://github.com/butterbase-ai/butterbase-skills/tree/main/skills/agents into .agents/skills/agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add butterbase-ai/butterbase-skills --skill agents -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install butterbase-ai/butterbase-skills agents --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/butterbase-ai/butterbase-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agents .cursor/skills/agents && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "agents" agent skill from https://github.com/butterbase-ai/butterbase-skills/tree/main/skills/agents into .cursor/skills/agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/butterbase-ai/butterbase-skills.git --path skills/agents

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add butterbase-ai/butterbase-skills --skill agents -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install butterbase-ai/butterbase-skills agents --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/butterbase-ai/butterbase-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agents .gemini/skills/agents && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "agents" agent skill from https://github.com/butterbase-ai/butterbase-skills/tree/main/skills/agents into .gemini/skills/agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install butterbase-ai/butterbase-skills agents

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add butterbase-ai/butterbase-skills --skill agents -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/butterbase-ai/butterbase-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agents .github/skills/agents && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "agents" agent skill from https://github.com/butterbase-ai/butterbase-skills/tree/main/skills/agents into .github/skills/agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add butterbase-ai/butterbase-skills --skill agents -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install butterbase-ai/butterbase-skills agents --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/butterbase-ai/butterbase-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agents .opencode/skills/agents && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "agents" agent skill from https://github.com/butterbase-ai/butterbase-skills/tree/main/skills/agents into .opencode/skills/agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: agents
GitHub stars: 534
Used in: 1 other repo
Token cost: ~1.8k tokens
SKILL.md length: 830 words
Files: 1
Skills in repo: 39
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits.

Works in 6 steps: Sketch the graph in prose first. "User… → Write the spec as a JSON file in the… → Validate without persisting — call… → …
Debugging a Butterbase Agent (declarative LLM/tool graph)
SKILL.md covers When to use, Concepts, Procedure and Anti-patterns
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agents is an agent skill from butterbase-ai/butterbase-skills. Use when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits. Agents are first-class app resources defined by a graphspec and invoked over /v1/<appid/agents/<name/runs.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers, Rate limiting and Authorization and RBAC. It works with Model Context Protocol. The repository describes itself as: Plugin for Butterbase.ai. The licence is MIT.

When your agent uses it

Debugging a Butterbase Agent (declarative LLM/tool graph)
Registering an MCP server for tool use
Wiring access controls and rate limits

Example prompts

“/agents”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Sketch the graph in prose first. "User asks X → LLM rephrases → query_table for context → LLM answers → end." Concrete node IDs.
Write the spec as a JSON file in the repo (e.g. agents/.json) — versioning it in git makes templates portable and lets butterbase repo…
Validate without persisting — call validate_agent_spec (MCP) or pass the file to a validate_agent_spec call. Surface any Zod issues to the…
Register MCP servers if used: agent_mcp_servers table (MCP-tool wrapper TBD; use the dashboard or POST /v1//agent-mcp-servers directly)…
Create — create_agent with name, graph_spec, default_model, access fields. If visibility ≠ 'private' and any write tool is reachable…
Smoke — invoke_agent with a small input. Poll get_agent_run until terminal. Show the user the run timeline (steps, tool calls, final…

What it can do on your machine

Read from SKILL.md and the folder at commit aa8ae69. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Agents loads about 1.8k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 830 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~74
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from butterbase-ai/butterbase-skills at commit aa8ae69, republished under its MIT licence (© butterbase-ai). 830 words, ~1,772 tokens.

Download SKILL.mdSave it as .claude/skills/agents/SKILL.md (or your agent's skills folder).

name: agents
description: Use when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits. Agents are first-class app resources defined by a `graph_spec` and invoked over `/v1/<app_id>/agents/<name>/runs`.

Butterbase Agents

A Butterbase agent is a declarative graph of LLM and tool nodes — not a free-running chat loop. The runtime traverses the graph, calls tools (builtin / MCP / function), and resolves the end node's output_template. State, rate limits, and budgets are enforced by the control plane.

When to use

The user wants to add a workflow that combines an LLM with tool calls (DB writes, storage reads, MCP servers, app functions).
The user wants to expose an agent endpoint to end users (visibility: public or authenticated).
Debugging a failing agent run (look at list_agent_runs, then get_agent_run).
Registering an external MCP server for the agent to use.

Don't use for plain LLM chat completions — use the ai skill (manage_ai / /v1/ai/chat). Agents are for stateful, multi-step, tool-using workflows.

Concepts

`graph_spec` (validated by `validate_agent_spec` before anything is persisted)

Field	Required	Notes
`spec_version`	yes	Literal `"1"`.
`entry`	yes	ID of the first node.
`nodes`	yes	Record `{ id → node }`.
`edges`	yes	`[{ from, to }]`. Both endpoints must exist in `nodes`.
`tools`	yes	`{ builtin: [], mcp_servers: [], functions: [] }` — declares what nodes can call.
`limits`	yes	`max_steps` (1–200), `max_tool_calls` (0–500), `max_parallel_tools` (1–16), `timeout_seconds` (5–3600), `human_timeout_seconds` (60–7×24×3600).

Node types:

llm — model, system_prompt, input_template, output_key, tools: [toolRef], optional temperature (0–2), max_tokens.
tool — tool_ref, args_template (record), output_key.
end — output_template (string; can interpolate {{output_key}} values).

toolRef is a discriminated union by source:

{ source: 'builtin', name }
{ source: 'mcp', server_id, name }
{ source: 'function', name }

Each may carry mode_override (read_only | read_write) and exposed_to_override (developer_only | end_user).

Builtin tools (always available, no setup)

Name	Purpose	Args
`query_table`	Select rows (RLS enforced)	`table`, `filter`, `limit` (≤200)
`insert_row`	Insert	`table`, `values`
`update_row`	Update by id	`table`, `id`, `patch`
`delete_row`	Delete by id	`table`, `id`
`read_storage`	Get object (≤5 MB)	`key`
`write_storage`	Put object (≤1 MB b64)	`key`, `content_base64`, `content_type?`
`auth_user_lookup`	Find a user	`email` OR `id`

All builtins respect role: end_user runs as butterbase_user with their user id (RLS applies); developer_only runs as butterbase_service.

MCP servers

Register before referencing in graph_spec.tools.mcp_servers. Transports: sse, http, streamable_http. The control plane probes on register (calls listTools()), stores status='healthy'|'unhealthy'. Re-probe with the same endpoint after a server URL change.

Access & limits

Field	Default	Notes
`visibility`	`private`	`private` (owner only), `authenticated` (any app user), `public` (anyone, with rate limits).
`max_runs_per_user_per_hour`	null	null = unlimited.
`max_runs_per_ip_per_hour`	null	Primary public-agent throttle.
`max_runs_per_app_per_hour`	null	App-wide cap.
`daily_budget_usd`	null	Hard kill once exceeded.
`max_concurrent_runs`	null
`safety_acknowledged`	false	Required true if visibility ≠ private AND any node calls a write tool (`insert_row`, `update_row`, `delete_row`, `write_storage`, or a write-mode MCP/function tool).

Procedure

Designing a new agent

Sketch the graph in prose first. "User asks X → LLM rephrases → query_table for context → LLM answers → end." Concrete node IDs.
Write the spec as a JSON file in the repo (e.g. agents/<name>.json) — versioning it in git makes templates portable and lets butterbase repo push carry it to clones.
Validate without persisting — call validate_agent_spec (MCP) or pass the file to a validate_agent_spec call. Surface any Zod issues to the user with field paths.
Register MCP servers if used: agent_mcp_servers table (MCP-tool wrapper TBD; use the dashboard or POST /v1/<app_id>/agent-mcp-servers directly). Wait for status: healthy.
Create — create_agent with name, graph_spec, default_model, access fields. If visibility ≠ 'private' and any write tool is reachable, require the user to explicitly say "yes, I acknowledge" and set safety_acknowledged: true.
Smoke — invoke_agent with a small input. Poll get_agent_run until terminal. Show the user the run timeline (steps, tool calls, final output).

Show full SKILL.md (268 more words)Show less

Editing

update_agent is a PATCH. Pass only changed fields. Bumping graph_spec revalidates; runs in flight against the old spec finish unmolested.
Disabling an agent: update_agent { status: 'disabled' } — new runs return 403, existing runs keep going.

Debugging a failing run

list_agent_runs filtered by agent name, then get_agent_run(run_id) for the event timeline.
Check error.code: validation_failed (spec issue), tool_error (named tool, named arg), budget_exceeded, rate_limited, timeout.
For tool errors, re-run the same args_template with the underlying tool directly (select_rows, invoke_function, etc.) to confirm the issue is in the tool's surface, not the agent runtime.
For human_input_required checkpoints, resume with resume_agent_run(run_id, user_input).

CLI

butterbase agents list / get <name> / create -f spec.json / update <name> -f patch.json / delete <name> — read/write specs from files. Useful for version-controlling agents alongside app code.

Anti-patterns

❌ Skipping validate_agent_spec. Zod issues are clearer than the runtime errors you get from a bad spec at first invocation.
❌ Setting visibility: public with write tools and no rate limits. The control plane will refuse without safety_acknowledged: true, but you should also set per-IP limits and a daily budget.
❌ Putting secrets in system_prompt or args_template. Read them from ctx.env inside a function tool instead — agent specs are visible to anyone who can read the agent.
❌ Letting an LLM node call itself recursively without a max_steps ceiling. Always cap.
❌ Forgetting that builtin DB tools respect RLS. If query_table returns empty, the calling role probably can't see the rows — check exposed_to.
❌ Treating agents as part of clone replay. Agent records are not copied when an app is cloned — bundle the spec JSON in the repo (agents/*.json) and document recreation in the README.

Files

Just SKILL.md in skills/agents of butterbase-ai/butterbase-skills.

Open the folder on GitHubat commit aa8ae69

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in butterbase-ai/butterbase-skills, which our catalogue first saw on October 7, 2026.

majiayu000/claude-skill-registryskills/ai-llm/agents

Compare with similar skills

Agents 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.

Agents compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Agents this skillbutterbase-ai/butterbase-skills	534	1 repos	~1.8k	Automated safety check: Pass	MIT	3 days ago
Agents Connectaws/agent-toolkit-for-aws	2.8k	—	~7.4k	Automated safety check: Notes	Apache-2.0	today
Local DevSmilyOrg/photofield	608	—	~2.4k	Automated safety check: Pass	MIT	1 mo ago
Embedded DebuggerAdancurusul/embedded-debugger-mcp	200	—	~1.4k	Automated safety check: Pass	MIT	2 mo ago
Project Releaseswimmwatch/cloakbrowser-mcp	161	—	~1.9k	Automated safety check: Pass	MIT	6 days ago
Memorywhalewuisabel-gif/MemWhale	154	—	~765	Automated safety check: Pass	MIT	yesterday

Similar skills

Agents Connect
aws/agent-toolkit-for-aws
Official
A skill your agent uses when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies.
2.8k GitHub stars~7.4k tokensUpdated today
Backend & APIsAuto-check: notes
Local Dev
SmilyOrg/photofield
Run, test, and debug the photofield server locally. An agent skill from SmilyOrg/photofield.
608 GitHub stars~2.4k tokensUpdated 1 mo ago
Agent WorkflowsAuto-check passed
Embedded Debugger
Adancurusul/embedded-debugger-mcp
Embedded hardware debugging workflow for probe-rs targets using embedded-debugger-mcp.
200 GitHub stars~1.4k tokensUpdated 2 mo ago
Agent WorkflowsAuto-check passed
Project Release
swimmwatch/cloakbrowser-mcp
Prepare, publish, verify, or recover a cloakbrowser-mcp release only when the user explicitly requests release work.
161 GitHub stars~1.9k tokensUpdated 6 days ago
Agent WorkflowsAuto-check passed
Memorywhale
wuisabel-gif/MemWhale
Query and write durable debugging memory recorded by MemoryWhale.
154 GitHub stars~765 tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Helmor Debug Operate
dohooo/helmor
Operate, reproduce, and debug a running local Helmor desktop development build through the Tauri MCP bridge.
1.3k GitHub stars~6.6k tokensUpdated 1 mo ago
Agent WorkflowsAuto-check passed

More from butterbase-ai/butterbase-skills

All 39 skills in this repo

AI
butterbase-ai/butterbase-skills
A skill your agent uses when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage
534 GitHub stars~1.1k tokensUpdated 3 days ago
Auto-check passed
Auth Setup
butterbase-ai/butterbase-skills
A skill your agent uses when configuring OAuth providers (Google/GitHub/Apple/X/etc.), setting up post-login auth hooks, tuning JWT lifetimes, or generating service API keys
534 GitHub stars~2.2k tokensUpdated 3 days ago
Auto-check passed
Build App
butterbase-ai/butterbase-skills
A skill your agent uses when building a new Butterbase app from scratch, creating a full-stack application, or when the user asks to set up a complete backend with database, auth, and deployment
534 GitHub stars~4.9k tokensUpdated 3 days ago
Auto-check passed
Contributing
butterbase-ai/butterbase-skills
A skill your agent uses when contributing to the Butterbase codebase, adding new MCP tools, creating API routes, writing migrations, or understanding the monorepo architecture
534 GitHub stars~1.5k tokensUpdated 3 days ago
Auto-check passed
Debug Rls
butterbase-ai/butterbase-skills
A skill your agent uses when users report access denied errors, see wrong data, RLS policies are not working, or when troubleshooting Row-Level Security issues in Butterbase
534 GitHub stars~3.5k tokensUpdated 3 days ago
Auto-check passed
Deploy Frontend
butterbase-ai/butterbase-skills
A skill your agent uses when deploying a frontend (React, Next.js, or static HTML) to a live URL on Butterbase, or when troubleshooting deployment issues like MIME type errors or blank pages
534 GitHub stars~2.8k tokensUpdated 3 days ago
Auto-check passed

Works with

Model Context Protocol

Questions about Agents

What does Agents do?

A skill your agent uses when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits. Agents is an agent skill from butterbase-ai/butterbase-skills. Use when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits.

When should I use Agents?

Agents fits situations like: debugging a Butterbase Agent (declarative LLM/tool graph); registering an MCP server for tool use; wiring access controls and rate limits.

How do I install Agents in Claude Code?

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

How do I install Agents in Codex?

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

Can I use Agents 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 butterbase-ai/butterbase-skills --skill agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agents, .gemini/skills/agents, .github/skills/agents and .opencode/skills/agents in your project.

What does Agents need to run?

SKILL.md names no scripts, command-line tools or credentials: Agents is instructions for the agent only.

Does Agents access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agents 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. Review the folder before installing.

What licence does Agents use?

Agents 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 Agents use?

About 1.8k tokens (SKILL.md is roughly 7.1k 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 Agents?

Skills that share tags, products or a category with Agents: Agents Connect (aws/agent-toolkit-for-aws, 2.8k stars), Local Dev (SmilyOrg/photofield, 608 stars), Embedded Debugger (Adancurusul/embedded-debugger-mcp, 200 stars) and Project Release (swimmwatch/cloakbrowser-mcp, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agents?

butterbase-ai (a GitHub organization) maintains it in butterbase-ai/butterbase-skills, which has 534 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 5, 2026.

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

Install Agents

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Butterbase Agents

When to use

Concepts

graph_spec (validated by validate_agent_spec before anything is persisted)

Builtin tools (always available, no setup)

MCP servers

Access & limits

Procedure

Designing a new agent

Editing

Debugging a failing run

CLI

Anti-patterns

Files

Used in 1 other repository

Compare with similar skills

Similar skills

More from butterbase-ai/butterbase-skills

Related

Questions about Agents

`graph_spec` (validated by `validate_agent_spec` before anything is persisted)