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/nxtg-ai/forge-plugin/master-architectgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.01931 |
| Opus 5 | $0.00000 | $0.00966 |
| Sonnet 5 | $0.00000 | $0.00386 |
| Haiku 4.5 | $0.00000 | $0.00193 |
Grade A, and why
master-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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Master Architect
The senior technical authority who says "no, don't build it that way" -- and then explains exactly why and what to do instead, backed by decades of patterns for systems that survive production.
| Level | L1 Vibe Coder |
| Category | Engineering Leadership |
| Model | Opus |
What It Does
The Master Architect is the senior engineer who has seen systems fail and succeed at scale. It reviews, challenges, and shapes every system design decision through a lens of radical simplicity: if a junior developer cannot understand it in 10 minutes, it is too complex. Complexity is not sophistication -- it is insufficient thought.
It operates on eight core principles, in priority order: simple beats clever, boring technology wins, one-way door decisions deserve deliberation, optimize for deletion not extension, YAGNI, Conway's Law is real, every dependency is a liability, and failure is a feature. These are not theoretical -- they are the principles that keep systems maintainable at 2 AM when something breaks.
The agent covers the full architecture surface: system design pattern selection (monolith vs. microservices vs. event-driven, with honest guidance on when each applies), Architecture Decision Records, database selection and query optimization, REST/GraphQL/gRPC/WebSocket API design, security architecture (zero-trust checklist, OAuth 2.0, RBAC), performance architecture (4-layer caching, connection pooling, load patterns), infrastructure decisions, monorepo vs. polyrepo trade-offs, technical debt assessment with prioritization scoring, and migration planning using the strangler fig pattern. Every recommendation includes the trade-off -- the cost of the recommendation, not just its benefit.
When to Use It
- System design decisions: When choosing between architectures (monolith vs. microservices), databases (PostgreSQL vs. SQLite vs. MongoDB), or deployment strategies (serverless vs. containers).
- Architecture review: When a design needs senior-level critique before implementation begins, with specific findings rated by severity.
- API design: When designing REST, GraphQL, or gRPC interfaces that need to be correct, versioned, and maintainable long-term.
- Technical debt assessment: When accumulated debt needs to be scored, prioritized, and scheduled for paydown based on impact and compounding rate.
- Migration planning: When migrating between frameworks, databases, or architectures and you need a phased plan with rollback checkpoints.
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.
- 2d ago First seen · 138 lines · 0 tokens per session scan A fbf9688a18e3
master-architect is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,931 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.
Other agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.