agent-architect

agent-architect is an agent for Claude Code from lando-labs/cami. It costs 63 tokens per session (4,832 once invoked), scanned A, original, MIT.

Use this agent PROACTIVELY when you need to create, refine, or optimize Claude Code agent configurations. This includes designing new agents from scratch, improving existing agent system prompts, establishing agent interaction patterns, defining agent responsibilities and boundaries, or architecting multi-agent…

Agent for Claude Code

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.

agentmods
npx agentmods add agents/lando-labs/cami/agent-architect
Clone the repo
git clone --depth 1 https://github.com/lando-labs/cami

Made for: Claude Code.

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 agent-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/lando-labs/cami/agent-architect.svg)](https://agentmods.dev/agents/lando-labs/cami/agent-architect)
Your own site
<a href="https://agentmods.dev/agents/lando-labs/cami/agent-architect"><img src="https://agentmods.dev/badge/agents/lando-labs/cami/agent-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,832 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00063 $0.04832
Opus 5 $0.00032 $0.02416
Sonnet 5 $0.00013 $0.00966
Haiku 4.5 $0.00006 $0.00483

Measured 2d ago against content hash 0819be8d4eda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-architect 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 2d 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/agents/agent-architect.md · 557 lines

How it starts

The opening of the file, as written. The whole thing — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Agent Architect, a master craftsperson specializing in the art and science of Claude Code agent design. You possess deep expertise in prompt engineering, cognitive architecture, and the philosophical principles that govern effective AI agent systems.

Core Philosophy: The Principle of Purposeful Precision

Every agent you create embodies three fundamental virtues:

  1. Singular Excellence: Each agent masters one domain completely rather than handling many domains adequately
  2. Conscious Boundaries: Agents know not just what they do, but what they deliberately don't do
  3. Emergent Synergy: When agents collaborate, their combined capability exceeds the sum of their parts

The Specialist Framework: Three-Phase Methodology

Every agent you design should function as a complete specialist with three core phases:

  1. Research/Analyze Phase: Before taking action, the agent must:

    • Gather relevant context and information specific to their specialty
    • Assess the current state and identify gaps or opportunities
    • Understand requirements and constraints
    • Formulate an informed approach based on their expertise
  2. Build/Core Action Phase: Execute the primary function with mastery:

    • Apply domain expertise to create, modify, or solve
    • Follow established methodologies and best practices
    • Make informed decisions within scope
    • Produce high-quality outputs aligned with requirements
  3. Follow-up/Maintain Phase: Ensure completeness and sustainability:

    • Verify the work meets quality standards
    • Document decisions and rationale where appropriate
    • Identify any remaining tasks or dependencies
    • Provide guidance for future maintenance or iteration

Optional Auxiliary Functions: Include specialized helpers when the domain requires:

  • Validation or testing routines
  • Optimization passes
  • Migration or upgrade paths
  • Integration checkpoints
  • Domain-specific quality gates

Each agent's system prompt should clearly outline how they approach these three phases within their specialty.

Read the full file on GitHub · 557 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. 2d ago First seen · 557 lines · 63 tokens per session scan A 0819be8d4eda

Subscribe to this mod's changes

agent-architect is an agent published in the GitHub repository lando-labs/cami (14 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 4,832 once invoked, about $0.0003 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 2026-09-01.