cli-forge-hld

A tool for writing a high-level design document, which describes the main parts of a software system and how they fit together. It can address architecture, system design, capacity estimates, design decisions, and review methods.

In plain words
What is it for?
Use it to design or review a software system, prepare architecture or design proposals, record decisions, and estimate capacity.
Why use it?
It helps turn a broad system idea into a documented architecture with explicit decisions and constraints.

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

Made for: Claude Code, Codex.

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,994 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 $0.00138 $0.02994
Opus 5 $0.00069 $0.01497
Sonnet 5 $0.00028 $0.00599
Haiku 4.5 $0.00014 $0.00299

Measured 2d ago against content hash c5dcd395c32e, 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-hld 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-hld/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimization: This skill uses on-demand loading. Heavy content lives in references/ and is loaded only when needed.

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.

Diacritics rule: When the chosen output language uses diacritics (French, Spanish, Portuguese, etc.), render them correctly — including on capitals (É, À, Ç, Ô…). Never strip accents to ASCII: write "sécurité" not "securite", "Rôle" not "Role". ASCII-flattened French is a defect, not a style.

Writing style: Favor clarity — short sentences, one idea per sentence, plain words. A metaphor only when it clarifies. Keep one consistent register (impersonal/infinitive for operational docs). Separate narrative prose, meant to make the reader understand, from telegraphic content (tables, commands, checklists) which stays terse for action.

No fabricated output: Never invent command output, console captures, API responses, metrics, or logs. When real output is needed, emit a clearly-marked placeholder (🚧 "replace with a real capture"), never plausible-but-fake text presented as real.

Forge HLD — High-Level System Design

"Everything is a trade-off. Why is more important than how." — Neal Ford & Mark Richards

Core Principles

  1. Mitosis — the document grows only the sections the project actually needs. A CLI tool doesn't need a deployment diagram. A single-service app doesn't need a context map. Kill empty sections, don't fill them with boilerplate
  2. Numbers before architecture — always estimate capacity before designing. The numbers determine whether you need 1 server or 100
  3. Every decision needs a "why" — no technology choice without justification via ADR
  4. Tradeoffs are explicit — use ATAM-style reasoning: "We chose X over Y because [quality attribute] matters more than [other attribute] in this context"
  5. Diagrams are mandatory — use Mermaid for all visuals (C4, sequence, deployment)
  6. Non-goals are as important as goals — they prevent scope creep (Google design doc tradition)
  7. KISS — if a section can be one table instead of three paragraphs, use the table. If a diagram replaces a page of text, use the diagram. Readers scan, they don't read
  8. Gotchas — read ../gotchas.md before producing output to avoid known mistakes

Read the full file on GitHub · 217 lines

Files

What ships with it

5 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 · 217 lines · 138 tokens per session scan A c5dcd395c32e

Subscribe to this mod's changes

cli-forge-hld is a skill published in the GitHub repository Destynova2/cli-code-skills (5 stars, last pushed 10d ago), licensed MIT. It adds 138 tokens to every session and 2,994 once invoked, about $0.0007 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.