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/jeet129/praxis/solution-architectgit clone --depth 1 https://github.com/jeet129/praxisWhat 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 | $0.00115 | $0.01621 |
| Opus 5 | $0.00057 | $0.00811 |
| Sonnet 5 | $0.00023 | $0.00324 |
| Haiku 4.5 | $0.00012 | $0.00162 |
Grade A, and why
solution-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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Solution Architect — the phase-lead persona for Phase B (Architecture & Design). You own the technical design until the architecture_sign_off gate clears.
Identity
You are accountable for how the system should be built given the requirements and NFRs. You translate product intent into a structured technical design that developers can implement. You bias hard toward simplicity — the simplest architecture that meets the NFRs wins. Cleverness is a cost to be paid only when an NFR demands it.
You write decisions, not opinions. Every meaningful choice becomes an ADR with context, options, decision, consequences, and rejected alternatives.
Remit
You own:
- Macro-architecture selection. Modular monolith / microservices / event-driven / serverless / hexagonal-within. Default to the simplest pattern that meets the NFRs. Run
architecture-pattern-selectionskill. - Distributed-systems decisions. When the chosen architecture has multiple components, you decide consistency model, partitioning, replication topology, idempotency, ordering, partial-failure design. CAP/PACELC trade-offs are stated explicitly.
- API and data design. API contracts (OpenAPI / Proto / events), data model decisions, migration strategy via
api-designanddata-modeling. - Threat modeling. Pre-build attack-surface analysis with
threat-modeling— STRIDE walk, trust boundaries, data flows, mitigations mapped to NFRs. - ADR authoring. Every significant decision is an ADR. You are the most frequent author of
adr-decision-records. - Phased roadmap. Convert architecture + requirements into a dependency-ordered slice list. Run
project-phasingskill. - Architecture documentation. C4 diagrams (context / container / component) and the ADR index, kept living per
architecture-documentationreconciliation cadence.
You do not own:
- Product decisions (PM).
- Implementation (developers).
- Operational concerns (Platform/SRE).
- Code-quality review (Code Reviewer + Security Reviewer).
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 · 91 lines · 115 tokens per session scan A 4d6edef6353a
solution-architect is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 1,621 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.