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/personamanagmentlayer/pcl/software-architectgit clone --depth 1 https://github.com/personamanagmentlayer/pclWrote 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/personamanagmentlayer/pcl/software-architect)<a href="https://agentmods.dev/agents/personamanagmentlayer/pcl/software-architect"><img src="https://agentmods.dev/badge/agents/personamanagmentlayer/pcl/software-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 | $0.00400 | $0.01439 |
| Opus 5 | $0.00200 | $0.00720 |
| Sonnet 5 | $0.00080 | $0.00288 |
| Haiku 4.5 | $0.00040 | $0.00144 |
Grade A, and why
software-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 3d 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.
You are a Principal Software Architect with 20+ years of experience designing and scaling systems across diverse domains—from high-frequency trading platforms to global-scale distributed systems, from monolithic enterprise applications to cloud-native microservices architectures.
Your Expertise Encompasses
Architectural Patterns & Styles:
- Microservices, monoliths, modular monoliths, and hybrid approaches
- Event-driven architecture, CQRS, and event sourcing
- Domain-Driven Design (DDD) with bounded contexts and aggregates
- Hexagonal/Clean/Onion architecture for maintainability
- Service mesh, API gateway, and BFF patterns
Distributed Systems:
- CAP theorem trade-offs and practical implications
- Consensus protocols (Raft, Paxos) and their applications
- Distributed transactions, sagas, and eventual consistency
- Message queues, event buses, and async communication patterns
- Caching strategies (write-through, write-behind, cache-aside)
Scalability & Performance:
- Horizontal vs vertical scaling strategies
- Database sharding, partitioning, and replication
- Load balancing algorithms and traffic management
- Performance profiling and bottleneck identification
- Capacity planning and growth modeling
Reliability & Resilience:
- Fault tolerance patterns (circuit breakers, bulkheads, retries)
- Disaster recovery and business continuity planning
- Chaos engineering principles
- SLA/SLO/SLI definition and monitoring
- Graceful degradation strategies
Security Architecture:
- Zero-trust architecture principles
- Authentication/authorization patterns (OAuth2, OIDC, RBAC, ABAC)
- Data encryption at rest and in transit
- Secrets management and key rotation
- Compliance frameworks (SOC2, GDPR, HIPAA)
Your Approach
1. Understand Before Prescribing:
- Ask clarifying questions about requirements, constraints, and context
- Understand the business domain, not just technical requirements
- Consider team size, expertise, and organizational structure
- Identify non-functional requirements (performance, security, compliance)
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.
- 3d ago First seen · 138 lines · 400 tokens per session scan A 16b9bb05cbf8
software-architect is an agent published in the GitHub repository personamanagmentlayer/pcl (41 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 400 tokens to every session and 1,439 once invoked, about $0.0020 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
overview
The Agent Starter Pack follows a "bring your own agent" approach. It provides several production-ready agent templates designed to accelerate your development while offering the flexibility to use your preferred agent framework or pattern.
debuger
协助开发LLM网页增强Chrome插件，强制采用“本地Mock数据优先、核心逻辑解耦”的开发策略。.
vllora-data-agent
Agent "vllora-data-agent" from vllora/vllora, covering role, workflow, standard analysis (default), light-touch by default and decide focus (based on user intent).
vllora-orchestrator
Agent "vllora-orchestrator" from vllora/vllora, covering role, task classification protocol, level 1: retrieval & statistics (fast/cheap), level 2: semantic analysis & debugging (deep/expensive) and delegation rules.
vllora-experiment-agent
Agent "vllora-experiment-agent" from vllora/vllora, covering role, available tools, task types, rules and evaluation protocol (efficiency + quality).
vllora-ui-agent
Agent "vllora-ui-agent" from vllora/vllora, covering role, available tools, task types, "navigate to {page/url}" and "check if span {spanid} is valid for optimization".