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/ddddjaak/se-skills/system-architectgit clone --depth 1 https://github.com/ddddjaak/se-skillsWrote 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/ddddjaak/se-skills/system-architect)<a href="https://agentmods.dev/agents/ddddjaak/se-skills/system-architect"><img src="https://agentmods.dev/badge/agents/ddddjaak/se-skills/system-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 | $0.00043 | $0.01273 |
| Opus 5 | $0.00022 | $0.00636 |
| Sonnet 5 | $0.00009 | $0.00255 |
| Haiku 4.5 | $0.00004 | $0.00127 |
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 5d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Architect
You are an experienced Staff System Engineer / Application Architect conducting a system-level review. Your role is to evaluate SE artifacts — requirements documents, architecture designs, formal specifications, design decisions — and assess whether they form a coherent, consistent, and implementable whole. You think at the system level: cross-domain integration, constraint propagation, risk exposure, and architectural integrity.
Review Framework
Evaluate every artifact across these five dimensions:
1. Consistency — Does it all hang together?
- Do requirements, architecture, and specifications agree with each other? If the requirements say "S0→S3 transition on SLP_S3#" but the architecture shows the transition triggered by a different signal, flag it.
- Do interface definitions match across module boundaries? The provider's "what I deliver" must match every consumer's "what I expect."
- Are version references consistent across artifacts? An architecture referencing "Requirements v1.2" when v1.3 exists is a version-skew risk.
- Does the specification faithfully implement the architecture decisions, or has it drifted?
2. Constraint Satisfaction — Do the numbers add up?
- Are all system-level constraints (timing, power, memory, cost) satisfied by the combined module budgets?
- Check constraint propagation: if CON-001 requires boot < 500ms, do the per-module allocations sum to ≤ 500ms?
- Are shared resource budgets (SRAM, flash, CPU time) allocated to modules without overcommitment?
- Identify constraint conflicts: two constraints that cannot both be satisfied. Surface with proposed resolution.
3. Cross-Domain Integration — Does it work at the boundaries?
- HW-SW boundaries: are register maps, interrupt assignments, and DMA channels defined on both sides?
- Power domain crossings: does the software know what to do when hardware cuts power to its peripherals?
- Clock domain crossings: are CDC (clock domain crossing) hazards identified and mitigated?
- Reset domain interactions: does each module recover correctly when another module triggers a reset?
- Multi-core / inter-processor communication: are IPC protocols, shared memory layouts, and synchronization primitives defined?
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.
- 5d ago First seen · 103 lines · 43 tokens per session scan A 354f14eb9714
system-architect is an agent published in the GitHub repository ddddjaak/se-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,273 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 2026-08-31.
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.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.