system-architecture-harness

system-architecture-harness is a skill for Codex from d4rkNinja/arcforge. It costs 88 tokens per session (7,132 once invoked), scanned A, original, MIT.

A structured method for designing and reviewing production software architecture. It turns requirements, risks, and constraints into explicit decisions that can be tested before or after launch.

In plain words
What is it for?
Use it for new systems, architecture reviews, monolith or microservice decisions, migrations, scaling, reliability, security, data ownership, and distributed workflows.
Why use it?
It prevents architecture choices from being based only on fashionable technologies or diagrams, and makes trade-offs and failure risks clear.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it for new systems, architecture reviews, monolith or microservice decisions, migrations, scaling, reliability, security, data ownership, and distributed workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/d4rkninja/arcforge/system-architecture-harness
Install

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.

Any agent
npx skills add d4rkNinja/arcforge --skill system-architecture-harness
Clone the repo
git clone --depth 1 https://github.com/d4rkNinja/arcforge

Made for: Codex.

Wrote 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.

agentmods badge for system-architecture-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/d4rkninja/arcforge/system-architecture-harness/github.svg)](https://agentmods.dev/skills/d4rkninja/arcforge/system-architecture-harness)
Your own site
<a href="https://agentmods.dev/skills/d4rkninja/arcforge/system-architecture-harness"><img src="https://agentmods.dev/badge/skills/d4rkninja/arcforge/system-architecture-harness/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.

agentmods 80×15 button for system-architecture-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/d4rkninja/arcforge/system-architecture-harness"><img src="https://agentmods.dev/badge/skills/d4rkninja/arcforge/system-architecture-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,132 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 438
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.07132
Opus 5 $0.00044 $0.03566
Sonnet 5 $0.00018 $0.01426
Haiku 4.5 $0.00009 $0.00713

Measured 5d ago against content hash 9284ce18efa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

system-architecture-harness 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.

skills/system-architecture-harness/SKILL.md · 486 lines

How it starts

The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Think Through Production Systems

Overview

Turn an idea, requirement set, existing codebase, incident pattern, or migration goal into an evidence-backed architecture that can be built, operated, reviewed, and evolved.

Core principle: Architecture is a chain of explicit decisions under constraints—not a diagram, a technology list, or a collection of fashionable patterns.

Non-Negotiable Architecture Law

NO ARCHITECTURE DECISION WITHOUT:
1. a requirement, invariant, risk, or constraint that motivates it;
2. at least one realistic alternative;
3. a stated trade-off and consequence;
4. a way to validate the decision in production or before launch.

A component without a responsibility is decoration. A database without access patterns and consistency semantics is guesswork. A queue without delivery, ordering, retry, and replay semantics is an outage waiting for a date.

A user-requested scope limit never waives an applicable correctness boundary. In particular, an offline mutation or collaboration design cannot be made backend-only: the client is a stateful system component whose authority, durable state, lifecycle, failure behavior, and recovery must be designed.

When to Use

Use this skill for:

  • greenfield system design;
  • architecture review or due diligence;
  • monolith/modular-monolith/microservice boundary decisions;
  • scaling, performance, reliability, or cost redesign;
  • data-platform, event-driven, real-time, financial, geospatial, storage, or AI systems;
  • cloud, on-premises, hybrid, multi-region, edge, or offline-first deployments;
  • migrations, decompositions, re-platforming, and legacy modernization;
  • production readiness, threat modeling, disaster recovery, and operational design;
  • architecture specifications, RFCs, ADRs, contextual AI reviews, and change handoff.

Do not use it as a substitute for product discovery, legal advice, formal safety certification, penetration testing, or domain-expert approval. It should expose when those are required.

Read the full file on GitHub · 486 lines

Files

What ships with it

38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago Changed · +10 lines 9284ce18efa8
  2. 9d ago First seen · 476 lines · 88 tokens per session scan A 0cb2b1599650

Subscribe to this mod's changes

system-architecture-harness is a skill published in the GitHub repository d4rkNinja/arcforge (16 stars, last pushed 5d ago), licensed MIT. It adds 88 tokens to every session and 7,132 once invoked, about $0.0004 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.