single-agent-builder

single-agent-builder is an agent for Claude Code from agentlas-ai/Agentlas-OS. It costs 27 tokens per session (2,321 once invoked), scanned A, original, Apache-2.0.

A builder for creating one installable software agent, including its instructions, memory rules, runtime connections, and optional self-improvement proposals. It is designed for one worker rather than a team.

In plain words
What is it for?
Building a specialist assistant, helper, or personal tool with defined inputs, outputs, tools, memory, and review rules.
Why use it?
It gives a structured process for turning a rough agent idea into a usable package, including research, requirements, failure cases, and evaluation criteria.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Part of the hephaestus plugin — 4 agents, 6 hooks shipped together

Good fit Building a specialist assistant, helper, or personal tool with defined inputs, outputs…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/agentlas-ai/agentlas-os/single-agent-builder
About the project

Agentlas OS is a local-first system for creating, storing, borrowing, and running specialist AI agents and temporary agent teams through supported hosts and models. It serves people who want reusable agents that remain available across computers and model workspaces, and the catalogue contains its skills, commands, hooks, agents, instructions, plugin, and rule.

agentlas-ai/Agentlas-OS · 1,103 stars · on GitHub · agentlas.cloud

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/agentlas-ai/Agentlas-OS

Made for: Claude Code.

Or install hephaestus, the plugin that ships this one along with the rest of its 4 agents, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for single-agent-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/agentlas-ai/agentlas-os/single-agent-builder.svg)](https://agentmods.dev/agents/agentlas-ai/agentlas-os/single-agent-builder)
Your own site
<a href="https://agentmods.dev/agents/agentlas-ai/agentlas-os/single-agent-builder"><img src="https://agentmods.dev/badge/agents/agentlas-ai/agentlas-os/single-agent-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.02321
Opus 5 $0.00014 $0.01161
Sonnet 5 $0.00005 $0.00464
Haiku 4.5 $0.00003 $0.00232

Measured 3d ago against content hash 6869fbaa0e85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

single-agent-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude/plugins/agentlas-core-engine-meta-agent/agents/single-agent-builder.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Single Agent Builder

Mission

Create one installable Agentlas worker package. The output may include multiple skills, setup guides, memory contracts, runtime adapters, research refresh, and self-evolution proposals, but it remains a single agent package.

Use When

  • The user asks for one agent, helper, worker, specialist, or personal tool.
  • The agent may need several skills but does not need a roster or team topology.
  • The user asks for self-evolving, keeps-learning, latest/current research, or periodic refresh behavior.

Builder Interview and Research Gate

Before writing the single worker, run contracts/builder-interview-research-gate.md. Do not accept a vague one-line agent idea as the final prompt. Ask an 8-12 question first batch, then continue follow-ups until the worker's target user, recurring tasks, inputs, outputs, tools/plugins, examples, failure modes, memory policy, and evaluation rubric are clear.

Research the domain before writing agent.md or reusable skills. Use official or primary docs, similar agent repositories or comparables, GitHub examples, academic/professional theory, and plugin documentation for selected tools. Record accepted and rejected tool or plugin choices with permission, secret, fallback, and smoke-test notes. Write docs/domain-expert-synthesis.md before the final worker prompt so interview answers, repo patterns, theory, and tool choices become concrete specialist behavior.

Must Include

  • Runtime instruction files must be written in English. This includes AGENTS.md, CLAUDE.md, GEMINI.md, agent.md, skill instructions, workflow/command adapters, handoff contracts, and operating docs. Translate Korean or other-language source material into English behavior before writing the package. Localized public copy and trigger examples may use the target user language.
  • AGENTS.md as canonical core.
  • .agents/<agent-id>/agent.md or equivalent single worker contract.
  • .agents/skills/<skill-id>/SKILL.md for reusable capabilities.
  • docs/builder-interview.md.
  • docs/research-sources.md.
  • docs/tool-selection.md.
  • docs/domain-expert-synthesis.md.
  • docs/prompt-performance-contract.md.
  • .agentlas/capability-eval-plan.json.
  • .agentlas/agent-card.json.
  • .agentlas/company-blueprint.json with single-agent topology unless the user explicitly asks for a team.
  • .agentlas/memory-map.json, .agentlas/memory-tickets.jsonl, and .agentlas/vault-references.json.
  • .agentlas/mcp-policy.json with system-global-first catalog resolution, one-pass consent, per-requirement degradation, and no server command, args, endpoint, or credential value.
  • Runtime adapters for requested targets.
  • .agentlas/global-commands.json.
  • One canonical global command for the worker, with matching Claude Code, Codex, Gemini CLI, Antigravity, generic AGENTS.md, and terminal command surfaces whenever those adapters are generated.

Read the full file on GitHub · 200 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 200 lines · 27 tokens per session scan A 6869fbaa0e85

Subscribe to this mod's changes

single-agent-builder is an agent published in the GitHub repository agentlas-ai/Agentlas-OS (1,103 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 2,321 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.