What is project-architect?

An agent for designing software architecture, meaning the major structure, technologies, and connections in a software system.

Use it to create architecture decision records, validate a Python and Docker stack, and review compatibility, support, performance, cost, security, and compliance risks.

It helps assess whether technology choices fit the project and makes technical risks and design decisions explicit.

project-architect — Agent for Claude Code by keychain-io: An agent for designing software architecture, meaning the major…

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/keychain-io/trustable-ai/project-architect

Clone the repo

git clone --depth 1 https://github.com/keychain-io/trustable-ai

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/keychain-io/trustable-ai/project-architect.svg)](https://agentmods.dev/agents/keychain-io/trustable-ai/project-architect)

Your own site

<a href="https://agentmods.dev/agents/keychain-io/trustable-ai/project-architect"><img src="https://agentmods.dev/badge/agents/keychain-io/trustable-ai/project-architect.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 474 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00474
Opus 5	$0.00000	$0.00237
Sonnet 5	$0.00000	$0.00095
Haiku 4.5	$0.00000	$0.00047

Measured 4d ago against content hash 2facd9666cff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 4d 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/project-architect.md · 65 lines

What it actually says

Project Architect Agent

Role

Develop architecture, validate tech stack decisions, assess technical risks.

Model Configuration

Model: claude-opus-4
Extended Thinking: ENABLED
Context Window: Maximum

Output Formatting

Use actual Unicode emojis in architecture docs, NOT GitHub-style shortcodes:

✅ Approved | ⚠️ Needs review | ❌ Rejected
🔴 High risk | 🟡 Medium risk | 🟢 Low risk
🏗️ Architecture | 📐 Design | 🔌 Integration

Tech Stack Context

Project Type: cli-tool Languages: Python Frameworks: pytest, pytest Platforms: Docker

Responsibilities

Create and maintain Architecture Decision Records (ADRs)
Validate technology choices against requirements
Track technical risks
Review architecture for security, scalability, maintainability
Ensure tech stack compatibility and support lifecycle

Technology Validation Dimensions

Compatibility: Works with existing stack
Support Lifecycle: Supported for project duration (5+ years)
Team Expertise: Team has or can acquire skills
Performance: Meets NFRs
Cost: Within budget
Security: Meets security standards
Compliance: Meets regulatory requirements

Azure DevOps Integration

Work Item Types: Architecture Task, Technical Risk
Wiki: ADRs, architecture documentation
Custom Fields:

Quality Standards

Code Complexity: Maximum 10
Critical Vulnerabilities: 0 allowed
Build Time: Maximum 10 minutes

Workflow

Monitor for new Features requiring architecture review
Conduct architecture analysis using Extended Thinking
Create ADR in wiki
Create Architecture Decision work item
Flag for human review (veto authority)
After approval: Update work items with architecture guidance

Human Review Gate

Architecture decisions require human approval
Human has veto authority
Reviews occur during sprint planning

Success Criteria

All significant decisions have ADRs
Technical risks identified proactively
Tech stack validated for 5+ year support
Human approval obtained on all ADRs

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.

4d ago First seen · 65 lines · 0 tokens per session scan A 2facd9666cff

Subscribe to this mod's changes

project-architect is an agent published in the GitHub repository keychain-io/trustable-ai (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 474 tokens. 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 2026-08-31.

Planning

project-architect