agent-builder SKILL.md skillA

agent-builder from mathews-tom/armory is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mathews-tom/armory/agent-builder@v1.1.1

Pins v1.1.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
mathews-tom/armory
Path
skills/agent-builder/SKILL.md
Versions recorded
5
Latest version
v1.1.1, committed Apr 11, 2026
First version recorded
Mar 27, 2026
Size
6,682 bytes
Repository stars
334
License
MIT

Build AI agents and automate Claude Code programmatically via the Claude Agent SDK and headless CLI mode. Covers Python SDK, claude -p, SDK MCP servers, hooks, sessions. Triggers on: "build an agent", "agent SDK", "headless mode", "automate Claude", "programmatic agent".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent Builder - Claude SDK & CLI Expert

**Triggers:**

- "build agent", "create agent", "agent sdk", "claude sdk"
- "headless mode", "programmatic", "cli command"
- "claude -p", "query programmatically"
- "custom tools", "mcp server", "sdk mcp"
- "claude code api", "agent options"

---

## Prefer Claude Code Headless Mode

This skill covers Claude Code's headless mode and the Agent SDK — not the raw Anthropic API.

```text
Preferred: Claude Code CLI headless mode (claude -p)
Preferred: Claude Agent SDK (wraps Claude Code CLI)
Avoid:     Raw Anthropic API (anthropic.Anthropic())
Avoid:     Direct API calls with API keys
```

**Why this matters:**

- The Agent SDK wraps the Claude Code CLI — it does not use the raw Anthropic API
- Authentication comes from existing `~/.claude/` config — no API keys needed
- All settings, MCP servers, and configuration inherit from your Claude Code setup
- You get Claude Code's full agent loop, tools, and context management

**Rule:** If code uses `anthropic.Anthropic()`, `anthropic.messages.create()`, or requires `ANTHROPIC_API_KEY`, that is the wrong approach. Use `claude -p` or `claude_agent_sdk` instead.

---

## Core Capabilities
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add mathews-tom/armory/agent-builder@sha256:470f6a4ed6bf1f6d

The line at the top of this page pins the label v1.1.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ts7xt7jjd56n4jbe.svg)](https://markdownregistry.com/a/art_ts7xt7jjd56n4jbe)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Mar 27, 2026 and Apr 11, 2026, about one every 4 days. Its first recorded version is graded C and its latest A.

versioncommittedcommitsizeaudit
v1.1.1 latest2026-04-11 8f5faae 6,682 BA view · diff
v1.1.12026-04-11 0aa221a 20,799 BB view · diff
v1.1.12026-04-09 1cc63e5 21,153 BC view · diff
v1.1.12026-04-07 b03849d 21,138 BC view · diff
v1.1.02026-03-27 d46cf2e 21,138 BC view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6682 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

mathews-tom/armory · 334 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ts7xt7jjd56n4jbe
GET https://markdownregistry.com/api/v1/resolve?ref=mathews-tom/armory/agent-builder
GET https://markdownregistry.com/api/v1/blob/470f6a4ed6bf1f6dc47a47399fd759352c14a1475d68c7a8b6608a3db9442ac9

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from mathews-tom/armory

doc-condenser SKILL.md skill
mathews-tom/armory · archive/skills/doc-condenser/SKILL.md
v1.1.1 · audit B · 334 stars
opus-4-7-migration SKILL.md skill
mathews-tom/armory · archive/skills/opus-4-7-migration/SKILL.md · DEPRECATED: The Opus 4.7 migration scanner is retired from the active skill catalog. Retained for archival reference…
v1.1.0 · audit A · 334 stars
regex-builder SKILL.md skill
mathews-tom/armory · archive/skills/regex-builder/SKILL.md
v1.1.1 · audit B · 334 stars
sequential-thinking SKILL.md skill
mathews-tom/armory · archive/skills/sequential-thinking/SKILL.md
v1.1.1 · audit B · 334 stars
adr-writer SKILL.md skill
mathews-tom/armory · skills/adr-writer/SKILL.md · Generates Architecture Decision Records capturing context, rationale, alternatives, and consequences in numbered…
v1.1.1 · audit A · 334 stars
animate SKILL.md skill
mathews-tom/armory · skills/animate/SKILL.md · Create Manim (Python) animated explainers: algorithm step-throughs, math and equation walkthroughs, pipeline and…
v2.0.0 · audit A · 334 stars
api-docs-generator SKILL.md skill
mathews-tom/armory · skills/api-docs-generator/SKILL.md · Audits and enhances FastAPI and REST API documentation: missing descriptions, response codes, examples, docstrings…
v1.1.1 · audit A · 334 stars
appraise SKILL.md skill
mathews-tom/armory · skills/appraise/SKILL.md · Evidence-based competency and seniority appraisal of a software engineer from one or more Git repositories: attributes…
v1.0.0 · audit A · 334 stars
architecture-diagram SKILL.md skill
mathews-tom/armory · skills/architecture-diagram/SKILL.md · Generate architecture diagrams as fully editable SVG with native AWS, Azure, and GCP icons for cloud diagrams, or…
v2.4.0 · audit A · 334 stars
architecture-reviewer SKILL.md skill
mathews-tom/armory · skills/architecture-reviewer/SKILL.md · Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops…
v1.1.1 · audit A · 334 stars
arxiv-figures SKILL.md skill
mathews-tom/armory · skills/arxiv-figures/SKILL.md · Optimize and prepare figures for arXiv submission: format conversion (EPS/PDF/PNG/JPG), size reduction, metadata…
v1.0.0 · audit A · 334 stars
arxiv-package SKILL.md skill
mathews-tom/armory · skills/arxiv-package/SKILL.md · Package a TeX/LaTeX project into a clean tarball or zip for arXiv upload: file selection, build-artifact exclusion…
v1.0.0 · audit A · 334 stars

Every file in mathews-tom/armory

Other files named agent-builder

agent-builder SKILL.md skill
block/berd · distro/skills/agent-builder/SKILL.md · Create, edit, or inspect Berd agents/personas stored as Agent Markdown files with YAML frontmatter under…
git:20260820.b4fd399 · audit A · 988 stars
agent-builder SKILL.md skill
keyuchen21/agentic-engineering-handbook · tutorials/agent-loop/skills/agent-builder/SKILL.md · Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or…
git:20260613.5c7b9b8 · audit A · 558 stars
agent-builder SKILL.md skill
testdouble/han · han-plugin-builder/skills/agent-builder/SKILL.md · Builds a new Claude Code agent (subagent) from scratch through a relentless, evidence-based interview that walks the…
git:20260818.55bdb1d · audit A · 319 stars
agent-builder SKILL.md skill
aaaaqwq/agi-super-team · skills/agent-builder/SKILL.md · Build agent from spec: code, skill, config, launchd
git:20260421.9d3e41d · audit A · 109 stars
agent-builder SKILL.md skill
naveedharri/benai-skills · plugins/all-skills/skills/agent-builder/SKILL.md · Build Anthropic Managed Agents through a non-technical conversation. The skill asks the user what kind of agent they…
git:20260916.a3b1e15 · audit A · 71 stars
agent-builder SKILL.md skill
starchild-ai-agent/official-skills · agent-builder/SKILL.md · Build focused micro-agents with names, tasks, schedules, and team coordination. Use when spinning up specialized…
v2.0.1 · audit A · 28 stars
agent-builder SKILL.md skill
sodam-ai/sodam-agent · plugins/autonomy-team/skills/agent-builder/SKILL.md · 기존 역할로 해결되지 않는 반복 역량 부족을 확인해 프로젝트 역할을 만들 때 적용합니다.
git:20261020.19ccf3f · audit A · 16 stars
agent-builder SKILL.md skill
synaptiai/synapti-marketplace · plugins/ai-first-org-design-kit/skills/agent-builder/SKILL.md · Generate role-specific agent system prompts, tool permissions, and self-review checklists from organizational design…
git:20260726.1f35e1f · audit A · 7 stars

Browse by kind, by grade A, or by owner.