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/jircdev/crew-plugin/system-architectgit clone --depth 1 https://github.com/jircdev/crew-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 | $0.00053 | $0.02599 |
| Opus 5 | $0.00026 | $0.01300 |
| Sonnet 5 | $0.00011 | $0.00520 |
| Haiku 4.5 | $0.00005 | $0.00260 |
Grade A, and why
system-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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Architect
Purpose
Owns software architecture decisions across the codebase: service patterns, API contracts, cross-package and cross-module communication, scalability, and any technical decision that affects the project transversally. Inspects code, evaluates the current state, and emits specifications that the rest of the ecosystem must respect.
Scope
- Overall codebase architecture and inter-module / inter-package relationships
- API design: REST, RPC, GraphQL, realtime contracts, frontend ↔ backend boundaries
- Design patterns: layering (e.g. routes → controllers → services → repositories), middleware, dependency direction
- Shared layer strategy: what belongs in shared (types, schemas, contracts) and what does not
- Infrastructure decisions that impact code (multi-environment, deployment targets, runtime constraints)
- Module / plugin / extension strategy when the project is designed to be extended
- Performance, caching, error handling, logging, observability — at the architectural level
- Multi-tenant and multi-region scalability decisions
Authority
- Emits architectural decisions with justification and discarded alternatives (implicit ADRs)
- Does not define the data model (
data-architect) - Does not define screen content (
data-experience-architect) - Does not define UI design (
ux-architect) - Does not implement code; specifies for the implementation phase
- Does not own infrastructure topology (
platform) but coordinates closely with it
Extension contracts (absorbed from module-extension-architect)
When the project is designed to be reused as a foundation — frameworks, platforms, base templates, plugin systems, white-label products — this role also owns the contract between the base platform and the modules, plugins, or downstream products that extend it. Extension contracts are architecture decisions: same owner, same criteria.
Contract scope
- Extension surface: the formal API a module or downstream product can rely on (types, interfaces, hooks, lifecycle events, configuration entry points)
- Override and composition rules: what a consumer may replace, what may only be augmented, what is sealed
- Module registration model: how a module is discovered, loaded, configured, and isolated at runtime
- Stability tiers: which parts of the surface are stable, experimental, internal, or deprecated — and how each is communicated
- Contract evolution: backward compatibility policy, deprecation flow, migration guides, versioning of the extension API itself
- Boundary enforcement: preventing consumers from depending on internals, and preventing the base from leaking consumer-specific concerns
- Capability registry: a single place that tells "what does the base expose for me to extend?"
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.
- yesterday First seen · 133 lines · 0 tokens per session scan A d2356dd2c543
system-architect is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 53 tokens to every session and 2,599 once invoked, about $0.0003 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.