Pydantic AI Harness
pydantic/pydantic-ai
Adds optional capabilities to Pydantic AI agents from pydantic-ai-harness, led by Code Mode, which runs many tool calls as one sandboxed Python script.
Helps design and build AI agents for any domain around a minimal loop of capabilities, knowledge and context, adding planning or subagents only when needed.
Install Agent Builder
$ npx skills add shareAI-lab/lab-skills --skill agent-builder -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shareAI-lab/lab-skills agent-builder --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-development/agent-builder .claude/skills/agent-builder && rm -rf skills-srcUse ~/.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/
Install the "agent-builder" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/agent-development/agent-builder into .claude/skills/agent-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-builder", 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 install https://github.com/shareAI-lab/lab-skills/tree/main/agent-development/agent-builderType 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.
$ npx skills add shareAI-lab/lab-skills --skill agent-builder -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shareAI-lab/lab-skills agent-builder --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agent-development/agent-builder .agents/skills/agent-builder && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-builder" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/agent-development/agent-builder into .agents/skills/agent-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-builder", 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.
$ npx skills add shareAI-lab/lab-skills --skill agent-builder -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shareAI-lab/lab-skills agent-builder --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agent-development/agent-builder .cursor/skills/agent-builder && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-builder" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/agent-development/agent-builder into .cursor/skills/agent-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-builder", 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 https://github.com/shareAI-lab/lab-skills.git --path agent-development/agent-builder--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add shareAI-lab/lab-skills --skill agent-builder -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shareAI-lab/lab-skills agent-builder --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agent-development/agent-builder .gemini/skills/agent-builder && rm -rf skills-srcUse ~/.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/
Install the "agent-builder" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/agent-development/agent-builder into .gemini/skills/agent-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-builder", 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.
$ gh skill install shareAI-lab/lab-skills agent-builderInstalls 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).
$ npx skills add shareAI-lab/lab-skills --skill agent-builder -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/agent-development/agent-builder .github/skills/agent-builder && rm -rf skills-srcUse ~/.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/
Install the "agent-builder" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/agent-development/agent-builder into .github/skills/agent-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-builder", 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.
$ npx skills add shareAI-lab/lab-skills --skill agent-builder -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shareAI-lab/lab-skills agent-builder --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agent-development/agent-builder .opencode/skills/agent-builder && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-builder" agent skill from https://github.com/shareAI-lab/lab-skills/tree/main/agent-development/agent-builder into .opencode/skills/agent-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-builder", 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
agent-builder- GitHub stars
- 314
- Token cost
- ~1.4k tokens
- SKILL.md length
- 628 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Helps design and build AI agents for any domain around a minimal loop of capabilities, knowledge and context, adding planning or subagents only when needed.
- Works in 3 steps: Capabilities (What can it DO?) → Knowledge (What does it KNOW?) → Context (What has happened?)
- Designing an agent for a customer service, research or operations task
- SKILL.md covers Applicability, The Core Philosophy, The Three Elements and Agent Design Thinking, plus 6 more sections
- Runs Python scripts from its folder
What it does
Agent Builder starts from the view that the model already knows how to act as an agent and the code should mostly stay out of its way. An agent is described as a simple loop in which the model sees context and available capabilities and decides whether to act or respond. Design comes down to three elements: the actions it can take, the knowledge it can load on demand, and the conversation history that links its actions.
The skill suggests starting with three to five capabilities and adding complexity in stages only when real use shows a need: progress tracking for long tasks, isolated subagents when exploration clutters context, and skills for domain expertise. Examples sketch agents for business, research and operations. Reference files include a minimal agent, a subagent pattern and tool templates in Python, plus a script to initialize a new agent project.
When your agent uses it
- Designing an agent for a customer service, research or operations task
- Deciding whether an agent needs planning, subagents or skills
- Understanding how coding agents like Claude Code are structured
Example prompts
- “Help me design an agent that triages our support inbox.”
- “Does my research assistant really need subagents, or is that overkill?”
- “Set up a minimal Python agent with search and file tools.”
Requirements
- Python for the reference agent code and init script
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit becee99. 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/ (Python), which the agent can run.
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
Agent Builder loads about 1.4k tokens when it runs, and up to ~8.3k if it reads all its reference files. Until then it costs about 134 tokens; SKILL.md has 628 words of instructions outside code blocks.
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 shareAI-lab/lab-skills at commit becee99, republished under its Apache-2.0 licence (© shareAI-lab). 628 words, ~1,407 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-builder/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- agent-builder
- description
- Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about AI coding agents, agent runtimes, or similar internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
Agent Builder
Build AI agents for any domain - customer service, research, operations, creative work, or specialized business processes.
Applicability
Treat the architecture and orchestration guidance as provider-agnostic. The bundled Python starter code currently uses the Anthropic SDK and an Anthropic model configuration; adapt that implementation layer when using another provider. Do not mistake the example client for a required agent architecture.
The Core Philosophy
The model already knows how to be an agent. Your job is to get out of the way.
An agent is not complex engineering. It's a simple loop that invites the model to act:
LOOP:
Model sees: context + available capabilities
Model decides: act or respond
If act: execute capability, add result, continue
If respond: return to userThat's it. The magic isn't in the code - it's in the model. Your code just provides the opportunity.
The Three Elements
1. Capabilities (What can it DO?)
Atomic actions the agent can perform: search, read, create, send, query, modify.
Design principle: Start with 3-5 capabilities. Add more only when the agent consistently fails because a capability is missing.
2. Knowledge (What does it KNOW?)
Domain expertise injected on-demand: policies, workflows, best practices, schemas.
Design principle: Make knowledge available, not mandatory. Load it when relevant, not upfront.
3. Context (What has happened?)
The conversation history - the thread connecting actions into coherent behavior.
Design principle: Context is precious. Isolate noisy subtasks. Truncate verbose outputs. Protect clarity.
Agent Design Thinking
Before building, understand:
- Purpose: What should this agent accomplish?
- Domain: What world does it operate in? (customer service, research, operations, creative...)
- Capabilities: What 3-5 actions are essential?
- Knowledge: What expertise does it need access to?
- Trust: What decisions can you delegate to the model?
CRITICAL: Trust the model. Don't over-engineer. Don't pre-specify workflows. Give it capabilities and let it reason.
Progressive Complexity
Start simple. Add complexity only when real usage reveals the need:
| Level | What to add | When to add it |
|---|---|---|
| Basic | 3-5 capabilities | Always start here |
| Planning | Progress tracking | Multi-step tasks lose coherence |
| Subagents | Isolated child agents | Exploration pollutes context |
| Skills | On-demand knowledge | Domain expertise needed |
Most agents never need to go beyond Level 2.
Domain Examples
Business: CRM queries, email, calendar, approvals Research: Database search, document analysis, citations Operations: Monitoring, tickets, notifications, escalation Creative: Asset generation, editing, collaboration, review
The pattern is universal. Only the capabilities change.
Show full SKILL.md (264 more words)Show less
Key Principles
- The model IS the agent - Code just runs the loop
- Capabilities enable - What it CAN do
- Knowledge informs - What it KNOWS how to do
- Constraints focus - Limits create clarity
- Trust liberates - Let the model reason
- Iteration reveals - Start minimal, evolve from usage
Anti-Patterns
| Pattern | Problem | Solution |
|---|---|---|
| Over-engineering | Complexity before need | Start simple |
| Too many capabilities | Model confusion | 3-5 to start |
| Rigid workflows | Can't adapt | Let model decide |
| Front-loaded knowledge | Context bloat | Load on-demand |
| Micromanagement | Undercuts intelligence | Trust the model |
Resource Routing
Load only what the current task needs:
| User need | Resource | Do not load when |
|---|---|---|
| Understand or debate the architecture | references/agent-philosophy.md | The user only needs runnable starter code |
| Inspect the smallest complete loop | references/minimal-agent.py | The task is conceptual or provider-neutral |
| Add or adapt individual capabilities | references/tool-templates.py | No implementation is requested |
| Design context-isolated child agents | references/subagent-pattern.py | A single-agent loop is sufficient |
| Generate a local Python starter project | scripts/init_agent.py | The user asked only for design advice |
The Python resources are learning-oriented examples, not a security boundary. Their shell capability requires user approval by default; production systems still need isolation, least privilege, audit logs, and policy appropriate to their threat model.
The Agent Mindset
From: "How do I make the system do X?" To: "How do I enable the model to do X?"
From: "What's the workflow for this task?" To: "What capabilities would help accomplish this?"
The best agent code is almost boring. Simple loops. Clear capabilities. Clean context. The magic isn't in the code.
Give the model capabilities and knowledge. Trust it to figure out the rest.
© shareAI-lab, Apache-2.0. 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 5 other files (scripts, references) in agent-development/agent-builder of shareAI-lab/lab-skills.
- SKILL.md
- references/agent-philosophy.md
- references/minimal-agent.py
- references/subagent-pattern.py
- references/tool-templates.py
- scripts/init_agent.py
Open the folder on GitHubat commit becee99
Compare with similar skills
Agent Builder 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Builder this skillshareAI-lab/lab-skills | 314 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Pydantic AI Harnesspydantic/pydantic-ai | 20k | — | ~4.9k | Automated safety check: Pass | MIT | |
| Agent Harness BuilderFareedKhan-dev/claude-code-from-scratch | 298 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Deep Agents Corelangchain-ai/langchain-skills | 1.3k | 1 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Openhands SDKOpenHands/extensions | 157 | — | ~6.9k | Automated safety check: Pass | MIT | |
| Swarms Multi-Agent Frameworkkyegomez/swarms | 7.2k | — | ~5.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Agent Harness Builder
FareedKhan-dev/claude-code-from-scratch
Gives patterns, a tool design checklist and an architecture decision tree for building agent harnesses, tools and multi-agent setups around a model.
- Official
Deep Agents Core
langchain-ai/langchain-skills
Explains how to build agents with the Deep Agents framework: create_deep_agent, the built-in middleware, the harness, SKILL.md format and configuration options.
Openhands SDK
OpenHands/extensions
Reference skill for the OpenHands Software Agent SDK - the Python framework for building AI agents that write software.
Swarms Multi-Agent Framework
kyegomez/swarms
Teaches the Swarms Python framework: the Agent class, tools, loops, memory and multi-agent structures such as sequential, concurrent and graph workflows.
Agent Squad Python Guide
2FastLabs/agent-squad
Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid.
More from shareAI-lab/lab-skills
All 10 skills in this repoDeep Architecture Research
shareAI-lab/lab-skills
Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions…
Neural Mechanism Research
shareAI-lab/lab-skills
Research why neural architectures and training methods work through forward computation, geometry, gradients, optimization dynamics, historical experiments, and competing explanations.
Review AI Conversations
shareAI-lab/lab-skills
Recover and review local human-AI conversations from Claude Code, Codex, opencode, Grok Build, and Cursor.
Skill Judge
shareAI-lab/lab-skills
Evaluate Agent Skill design quality with an opinionated, practice-derived rubric informed by public specifications and examples.
Understanding First Report
shareAI-lab/lab-skills
Reconstruct and report long-running or multi-turn research, architecture questions, reviews, decisions, completion results, and status as a clear, self-contained brief.
Vibe Coding
shareAI-lab/lab-skills
Transform an AI agent into a disciplined software development partner with strong judgment, transparent decisions, proportionate verification, and craftsmanship.
Related
Works with
Categories
Questions about Agent Builder
What does Agent Builder do?
Helps design and build AI agents for any domain around a minimal loop of capabilities, knowledge and context, adding planning or subagents only when needed. Agent Builder starts from the view that the model already knows how to act as an agent and the code should mostly stay out of its way. An agent is described as a simple loop in which the model sees context and available capabilities and decides whether to act or respond.
When should I use Agent Builder?
Agent Builder fits situations like: designing an agent for a customer service, research or operations task; deciding whether an agent needs planning, subagents or skills; understanding how coding agents like Claude Code are structured.
How do I install Agent Builder in Claude Code?
Run `npx skills add shareAI-lab/lab-skills --skill agent-builder -a claude-code`. Or copy the skill folder (agent-development/agent-builder in shareAI-lab/lab-skills) into .claude/skills/agent-builder in your project. Claude Code loads it when a task matches its description.
How do I install Agent Builder in Codex?
Run `npx skills add shareAI-lab/lab-skills --skill agent-builder -a codex`. Or copy the skill folder (agent-development/agent-builder in shareAI-lab/lab-skills) into .agents/skills/agent-builder in your project. Codex loads it when a task matches its description.
Can I use Agent Builder 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 shareAI-lab/lab-skills --skill agent-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-builder, .gemini/skills/agent-builder, .github/skills/agent-builder and .opencode/skills/agent-builder in your project.
What does Agent Builder need to run?
Going by SKILL.md and its folder, Agent Builder needs Python for the scripts in its folder. Our summary lists: Python for the reference agent code and init script.
Does Agent Builder 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 Agent Builder 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 Agent Builder use?
Agent Builder is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Builder use?
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.9k tokens, read only when the agent opens those files.
What are the alternatives to Agent Builder?
Skills that share tags, products or a category with Agent Builder: Pydantic AI Harness (pydantic/pydantic-ai, 20k stars), Agent Harness Builder (FareedKhan-dev/claude-code-from-scratch, 298 stars), Deep Agents Core (langchain-ai/langchain-skills, 1.3k stars) and Openhands SDK (OpenHands/extensions, 157 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Builder?
shareAI-lab (a GitHub organization) maintains it in shareAI-lab/lab-skills, which has 314 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 16, 2026.
Source: shareAI-lab/lab-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.