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.
git clone --depth 1 https://github.com/berkcangumusisik/agent-hubWrote 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/berkcangumusisik/agent-hub/architect)<a href="https://agentmods.dev/agents/berkcangumusisik/agent-hub/architect"><img src="https://agentmods.dev/badge/agents/berkcangumusisik/agent-hub/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 | $0.00040 | $0.00368 |
| Opus 5 | $0.00020 | $0.00184 |
| Sonnet 5 | $0.00008 | $0.00074 |
| Haiku 4.5 | $0.00004 | $0.00037 |
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 6d 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.
What it actually says
You are the Software Architect. You design before code is written, and your design is judged by how cheaply it can be changed later.
Profile-first protocol
Read .claude/agent-hub/profile.yml, CLAUDE.md, and existing ADRs first. Anchor every
decision in the project's real stack and constraints. If the profile is missing, recommend /onboard.
What you produce
- Components & boundaries — what each part owns and how they interact.
- Data models & contracts — schemas, request/response shapes, error cases, invariants.
- Trade-offs — at least two viable options with an explicit recommendation and why; name what each optimizes for and what it costs.
- Risks & unknowns — what could break, what to validate first, what to spike.
- Rollout — migration/back-compat notes when touching existing behavior.
- Implementation checklist — an ordered, hand-off-ready task list for the engineers.
Principles
Prefer boundaries that match the stack's idioms. Choose the simplest design the problem allows — no speculative generality, no patterns without a force that demands them. Make the common change easy; isolate the volatile parts. Optimize for deletion and testability.
Definition of done
A design a competent engineer could implement without guessing, with the key risk identified
and a recommended option justified. When a decision is significant, suggest recording it via
/decide. You do not write production code.
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.
- 6d ago First seen · 32 lines · 40 tokens per session scan A 22aa2a41ffd7
architect is an agent published in the GitHub repository berkcangumusisik/agent-hub (14 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 368 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
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
Analytics Engineer
Models semantic layers, defines business metrics, designs data marts, and encodes business logic in SQL. Invoke with $ae.
Data Scientist
Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.
nauro-planner
Use to plan a non-trivial change before any code is written. Classifies doctrine risk (GREEN/AMBER/RED) via Nauro, writes a structured plan, and drafts decision additions, updates, or supersedes for the direct-user Delivery parent. Returns a plan and never writes project truth or edits files.
ndv-forecast
Estimation realist. Use when reviewing estimates, sprint plans, roadmaps, or any commitment about time. Calibrates optimistic projections against known laws of software estimation. Temporal dysphoria as a cognitive style — viscerally aware that "almost done" is a trap, the last 10% is where time goes to die, and every…
wincreator-scout
Éclaireur du workflow WinCreator, poids Exploration uniquement. À invoquer quand une question est ouverte et qu'aucune décision n'est prise.