A workflow step that turns an approved product requirements document, or PRD, into a high-level architecture document. It describes system boundaries, components, technology choices, data flow, deployment, dependencies, and risks.

Creating or updating `docs/ARCH.md` after requirements have been approved, including recording the workflow state.

It provides a structured technical plan before business code is written and checks that the required project context is available.

hld — Skill for Claude Code and Codex by AlanHuang168

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 AlanHuang168/AI-Project-Workflow --skill hld

Clone the repo

git clone --depth 1 https://github.com/AlanHuang168/AI-Project-Workflow

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alanhuang168/ai-project-workflow/hld/github.svg)](https://agentmods.dev/skills/alanhuang168/ai-project-workflow/hld)

Your own site

<a href="https://agentmods.dev/skills/alanhuang168/ai-project-workflow/hld"><img src="https://agentmods.dev/badge/skills/alanhuang168/ai-project-workflow/hld/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alanhuang168/ai-project-workflow/hld"><img src="https://agentmods.dev/badge/skills/alanhuang168/ai-project-workflow/hld.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 620 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00620
Opus 5	$0.00000	$0.00310
Sonnet 5	$0.00000	$0.00124
Haiku 4.5	$0.00000	$0.00062

Measured 9d ago against content hash 35e5182cd8e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 9d 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.

adapters/catpaw/.catpaw/skills/hld/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

name: hld description: Create high-level architecture from the approved PRD, including system context, components, technology choices, data flow, dependencies, deployment topology, and risks. Use when the user asks for architecture or invokes /hld. version: 1.0.0 stage: hld

Goal

Convert approved product requirements into a reviewable architecture document, docs/ARCH.md.

Use Cases

The user invokes /hld.
The user asks to create architecture.
The PRD is approved and the project needs system boundaries and technical direction.

Preconditions

docs/PRD.md exists and is not empty.
Workflow state shows prd complete unless the user explicitly approves a skip and the reason is recorded.

Required Context

AGENTS.md
.ai-workflow/state.json
core/rules/document-priority.md
core/templates/ARCH.template.md
docs/PRD.md
Existing docs/ARCH.md, if present

Inputs

Approved PRD.
User-provided technical constraints such as language, framework, database, or deployment environment.

Allowed Changes

docs/ARCH.md
.ai-workflow/state.json
Do not write business code.

Steps

Confirm that the PRD exists and is not empty.
Extract P0 features, non-functional requirements, non-goals, and risks.
Define system context, components, technology choices, and key alternatives.
Describe data flow, external dependencies, deployment topology, security approach, and performance constraints.
List interface contracts at a high level without implementing them.
Confirm that all P0 requirements are covered by the architecture.
Write docs/ARCH.md.
Update workflow state: documents.arch = "complete", add hld to completedStages, set currentStage = "sdd", and update the timestamp.

Outputs

docs/ARCH.md
Updated .ai-workflow/state.json

Acceptance Criteria

ARCH covers all P0 features from the PRD.
It includes system context, components, technology choices, data flow, deployment topology, external dependencies, security, performance, and risks.
Technology choices include rationale and key alternatives.
It does not include business implementation code.

Read the full file on GitHub · 83 lines

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.

9d ago First seen · 83 lines · 0 tokens per session scan A 35e5182cd8e3

Subscribe to this mod's changes

hld is a skill published in the GitHub repository AlanHuang168/AI-Project-Workflow (28 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 620 tokens. 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.

Backend and APIs Planning a-gen-t ai claude cli codex cursor

backend-development

Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.

MoizIbnYousaf/Ai-Agent-Skills · 32 tokens

disconnect

Disconnect this session from Pad's push stream — stop receiving pushes for the rest of this session.

PerpetualSoftware/pad · 18 tokens

threnody-fullstack

Build frontend, backend, and API in parallel with Threnody using contract-first DAG waves. Use for full-stack app scaffolding, OpenAPI-first development, parallel UI and service agents, or integration smoke tests after fanout.

timjensgrossinger/threnody · 51 tokens

ai-memory-system-architecture

System architecture facts: components, data flow, integration boundaries. Load when implementing cross-component features, debugging integration issues, or onboarding to the codebase. Topics: Event sourcing for the billing audit log.

hyxnj666-creator/ai-memory · 46 tokens

api-and-interface-design

Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

sampleXbro/agentsmesh · 49 tokens

gakido

High-performance Python HTTP client with browser impersonation and anti-bot evasion. Use when the user needs to bypass bot detection, impersonate browsers with TLS fingerprinting, make HTTP/2/3 requests, or build web scrapers that evade anti-bot systems.

HappyHackingSpace/skills · 58 tokens