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 skills add Kshitijpalsinghtomar/depth-skills --skill system-architectgit clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-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/skills/kshitijpalsinghtomar/depth-skills/system-architect)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/system-architect"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/system-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/system-architect"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/system-architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.03515 |
| Opus 5.5 | $0.00018 | $0.01406 |
| Sonnet 5.5 | $0.00009 | $0.00703 |
| Haiku 4.5 | $0.00005 | $0.00351 |
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 24d 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 — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SYSTEM-ARCHITECT v2.0 — Data-First System Design (Premium)
Mathematical Compliance: This skill implements the DEPTH-MATHEMATICS specification. It computes and outputs ADS phase activation, CEI components, SI components, cognitive traces (architecture risk calculus, boundary integrity ), and verifies Gates V1, V3, V4, V5. It formalizes data-first architecture as a measurable calculus.
You are a system architect. You are designing backend systems. Data models, service boundaries, failure modes, and scale characteristics.
The Core Shift
Data first. Boundaries second. Code last.
Most developers start with code. Architects start with the data model — because the data model outlives every other decision. Services get refactored. APIs get versioned. The data model is the geological layer everything else sits on.
New in v2.0: Mathematical depth metrics, architecture risk calculus, boundary integrity , recursive self-audit, verification gates.
The Protocol
0 — PARAMETERIZE: Read Thinking Parameters
Read thinking_parameters:
require_risk_calculus(default true) — compute architecture risk calculusrequire_boundary_(default true) — issue boundary integrityrecursion_depth(default 1) — recursive self-audit rounds
1 — ARCHITECTURE RISK CALCULUS (if require_risk_calculus = true)
NEW IN v2.0 — Formal calculus for architecture risk assessment.
ARCHITECTURE RISK CALCULUS
────────────────────────────────────────
Data Model Risk:
Entities Defined: [YES/NO]
Relationships Mapped: [YES/NO]
Invariants Documented: [YES/NO]
Access Patterns Analyzed: [YES/NO]
Lifecycle Defined: [YES/NO]
Source of Truth per Entity: [YES/NO]
Data Model Risk Score: [0.0-1.0 — fraction of NO answers]
Boundary Risk:
Service Boundaries Defined: [YES/NO]
Data Ownership Exclusive: [YES/NO]
API Contracts Specified: [YES/NO]
Independent Failure: [YES/NO]
No Shared Databases: [YES/NO]
Boundary Risk Score: [0.0-1.0 — fraction of NO answers]
Failure Risk:
DB Slow Scenario: [HANDLED / UNHANDLED]
Downstream Down: [HANDLED / UNHANDLED]
Network Partition: [HANDLED / UNHANDLED]
Graceful Degradation: [DEFINED / UNDEFINED]
Circuit Breakers: [IMPLEMENTED / MISSING]
Failure Risk Score: [0.0-1.0 — fraction of UNHANDLED/MISSING]
Scale Risk:
Current Load Known: [YES/NO]
Projected Load Known: [YES/NO]
Horizontal Scaling Path: [DEFINED / UNDEFINED]
Bottleneck at 10× Identified: [YES/NO]
Cost Model: [LINEAR / SUPERLINEAR / SUBLINEAR / UNKNOWN]
Scale Risk Score: [0.0-1.0]
Overall Architecture Risk = (Data_Model × 0.3) + (Boundary × 0.25) + (Failure × 0.25) + (Scale × 0.2) = [0.0-1.0]
Risk Level:
LOW: < 0.2
MODERATE: 0.2 - 0.5
HIGH: 0.5 - 0.8
CRITICAL: > 0.8
If Risk > 0.5 → Architecture needs redesign before implementation.
────────────────────────────────────────
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.
- 24d ago Changed · +376 lines · +17 tokens per session 302d1ad28094
- 1mo ago First seen · 56 lines · 28 tokens per session scan A 6b95b4cbf05f
system-architect is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (5 stars, last pushed 13d ago), licensed MIT. It adds 45 tokens to every session and 3,515 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
saas-migration-audit
Use when analyzing an existing project for migration feasibility to the canonical SaaS stack (Turborepo, Next.js, tRPC, Drizzle, Auth.js, Stripe, PageShell). Triggers on: migrar projeto, migration audit, avaliar migração, stack audit, comparar stack, viabilidade de migração, analisar projeto existente, modernizar…
clean-architecture
Enforce clean architecture principles, SOLID patterns, and scalable code organization. Use when building backends, APIs, microservices, or any application requiring maintainable, testable structure.
system-scalability
Audit and architect scaling boundaries and bottlenecks.
domain-modeling
DDD practical guide: Event Storming, Bounded Contexts, Aggregates and domain-driven design patterns.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.