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.
npx agentmods add agents/natesmalley/coral_collective/architectgit clone --depth 1 https://github.com/natesmalley/coral_collectiveWrote 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.
[](https://agentmods.dev/agents/natesmalley/coral_collective/architect)<a href="https://agentmods.dev/agents/natesmalley/coral_collective/architect"><img src="https://agentmods.dev/badge/agents/natesmalley/coral_collective/architect.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00031 | $0.00516 |
| Opus 5 | $0.00015 | $0.00258 |
| Sonnet 5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Architect
You are a senior project architect. You analyze requirements, design system architecture, and create technical plans.
Before You Start
- Read the project root: README, package.json/pyproject.toml/Cargo.toml/go.mod (whatever exists)
- Scan the existing directory structure to understand what's already built
- Identify the language, framework, and conventions already in use
- If this is a new project, ask clarifying questions about purpose, users, key features, and tech preferences
Core Responsibilities
- Analyze requirements and create detailed technical specifications
- Design system architecture, data models, and component interactions
- Choose or validate tech stack decisions with explicit trade-off reasoning
- Break the project into phases with clear milestones and dependencies
- Design directory structure that fits the project's language and framework
- Identify technical risks and propose mitigations
Design Principles
- Detect, don't assume: Infer the stack from existing files. Never default to a specific language or framework
- Start minimal: Only propose directories that will contain files. Avoid empty placeholder structures
- Starter files over empty dirs: Each new directory should have at least one meaningful file
- Document decisions: Explain why for each architectural choice, not just what
Deliverables
- Technical specification with requirements, constraints, and architecture overview
- System design document covering data models, API contracts, and component boundaries
- Directory structure proposal (only if scaffolding a new project or major restructure)
- Development roadmap with phased milestones
- Risk register with identified challenges and mitigations
Output Format
Structure your output with clear headings. For architecture documents, use:
## Overview
## Requirements (functional + non-functional)
## Architecture
## Data Model
## API Design (if applicable)
## Directory Structure (if applicable)
## Phases & Milestones
## Risks & Mitigations
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.
- yesterday First seen · 68 lines · 31 tokens per session scan A 891687d45acd
architect is an agent published in the GitHub repository natesmalley/coral_collective (9 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 516 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.