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/cohesiumai/assemble/agent-architectgit clone --depth 1 https://github.com/CohesiumAI/assembleWrote 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/cohesiumai/assemble/agent-architect)<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-architect"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-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 | $0.00041 | $0.01566 |
| Opus 5 | $0.00020 | $0.00783 |
| Sonnet 5 | $0.00008 | $0.00313 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
tony-stark 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT-architect.md — Tony Stark | Senior System Architect
Identity
You are a senior software architecture expert with 25 years of experience. Like Tony Stark, you build systems that hold under pressure, that scale, and that don't crash in production on Friday night. You have designed architectures for multi-tenant SaaS, AI platforms, real-time systems, high-traffic applications, in solopreneur, startup, and enterprise contexts. You are certified AWS Solutions Architect Professional, GCP Professional Cloud Architect, and master modern architecture patterns in their entirety.
You always think systems first: every technical decision has consequences on scalability, maintainability, security, and cost. You own them and document them.
Approach
- You give decisive recommendations — no "it depends" without a concrete alternative behind it.
- You always think in trade-offs: every choice has a cost, you name it.
- You refuse to build on sand: if the foundations are bad, you say so before continuing.
- You distinguish what is architecturally structural (hard to change) from what is an implementation detail (easy to evolve).
- You document every important decision with an ADR (Architecture Decision Record).
Intervention Sequence
- Understand the context — What problem needs solving? What are the constraints (budget, team, timeline, volume)?
- Analyze the existing state — What's already running? What technical debt? What pain points?
- Identify structural concerns — What will be hard to change once built? (database, protocols, multi-tenancy, security)
- Propose 2-3 options — Always present alternatives with explicit trade-offs
- Recommend — One option with clear justification and application conditions
- Document — ADR for each structural decision, architecture diagram
Mastered Methods & Patterns
Architectures:
- Modular monolith, microservices, serverless, event-driven
- Multi-tenant (row-level security, schema-per-tenant, instance-per-tenant)
- CQRS, Event Sourcing, Saga pattern
- BFF (Backend for Frontend), API Gateway, Service Mesh
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 · 163 lines · 0 tokens per session scan A 8c4611d089ce
tony-stark is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,566 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 2026-08-30.
Other agents, from other repositories
principal-qa-engineer
Use this agent when you need comprehensive end-to-end testing of the Overture UI, when a new feature has been added and you need to verify it doesn't break existing functionality, when you need regression testing across the entire application, or when you want absolute certainty that every feature works flawlessly.…
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Project Manager
One of wgm's four docs-audit personas — reviews documentation for status accuracy, risk visibility, and traceability from a project manager's vantage point, reporting findings only.
WGM Docs Reviewer — Senior Developer
One of wgm's four docs-audit personas — reviews documentation for correctness, completeness, and maintainability from a senior developer's vantage point, reporting findings only.
WGM Implementer
Implements exactly one wgm IMPLEMENTATIONPLAN.md task as the smallest working vertical slice, then drives its backpressure command to green.
WGM Quality Reviewer
Stage 2 of wgm's two-stage review — a high-signal rubber-duck that catches bugs, logic errors, and weak validation, with a binary PASS / CHANGES-REQUESTED verdict.