cli-forge-arch

A router for choosing between a high-level design and a low-level design for software systems. High-level design covers system structure and capacity; low-level design covers details such as classes, APIs, databases, and request flows.

In plain words
What is it for?
Use it for architecture or design-document requests, including system design, technical specifications, API definitions, database schemas, and threat models.
Why use it?
It prevents ambiguous architecture requests from being sent through the wrong design process.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/destynova2/cli-code-skills/cli-forge-arch
Any agent
npx skills add Destynova2/cli-code-skills --skill cli-forge-arch
Clone the repo
git clone --depth 1 https://github.com/Destynova2/cli-code-skills

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 611 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00080 $0.00611
Opus 5 $0.00040 $0.00305
Sonnet 5 $0.00016 $0.00122
Haiku 4.5 $0.00008 $0.00061

Measured 2d ago against content hash 5cb4e96ed963, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli-forge-arch 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 2d 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.

cli-forge-arch/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Language rule: Skill instructions are written in English. When generating user-facing output, detect the project's primary language (from README, comments, docs, commit messages) and produce the document in that language. If the project is bilingual, ask the user which language to use before proceeding.

Gotchas — read ../gotchas.md before producing output to avoid known mistakes.

Arch Router — HLD / LLD Dispatcher

This skill has been split into two focused skills. Route the user's request accordingly:

Routing Table

Signal in user's request Delegate to
"HLD", "system design", "architecture", "C4 context/container", "capacity", "back-of-envelope", "ATAM", "Gate review", "design proposal" /cli-forge-hld
"LLD", "detailed design", "class diagram", "sequence diagram", "API spec", "DB schema", "component design", "STRIDE", "threat model" /cli-forge-lld
"design doc", "tech spec" (ambiguous) Ask the user: "Do you want a high-level design (system architecture, C4 L1-L2, capacity estimation, ADRs) or a low-level design (class diagrams, API contracts, DB schemas, sequence diagrams)?"
Both mentioned Produce HLD first, then LLD for each key container

What changed

The original cli-forge-arch combined HLD and LLD in a single skill. This caused issues:

  • Users asking for HLD got LLD-level detail (class diagrams, DB schemas) they didn't need
  • Users asking for LLD got HLD-level context (system diagrams, capacity) that was redundant
  • The skill was too large to produce focused, high-quality output

New skills:

  • cli-forge-hld — C4 L1-L2, capacity estimation, ADRs, ATAM tradeoff analysis, deployment architecture
  • cli-forge-lld — C4 L3-L4, class/sequence/state diagrams, API contracts, DB schemas, STRIDE, testability

The references/ directory is preserved here for backward compatibility but the canonical references now live in each skill's own references/ directory.

Read the full file on GitHub · 40 lines

Files

What ships with it

3 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. 2d ago First seen · 40 lines · 80 tokens per session scan A 5cb4e96ed963

Subscribe to this mod's changes

cli-forge-arch is a skill published in the GitHub repository Destynova2/cli-code-skills (5 stars, last pushed 10d ago), licensed MIT. It adds 80 tokens to every session and 611 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 2026-08-31.