draft-technical-architecture

draft-technical-architecture is a skill for Claude Code from dremonkey/agents-and-skills. It costs 70 tokens per session (674 once invoked), scanned A, original, MIT.

A procedure for drafting a concise technical specification for a small software component or bounded feature. It records decisions, interfaces, data flow, failure handling, assumptions, and trade-offs, with text diagrams.

In plain words
What is it for?
Use it for component architecture, a small subsystem, an RFC-style proposal, or an implementation-ready design; broader systems can be represented with Excalidraw visuals.
Why use it?
It turns a loosely defined engineering idea into notes that developers can review and implement, while keeping the scope manageable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agents-and-skills plugin — 8 skills shipped together

Good fit Use it for component architecture, a small subsystem, an RFC-style proposal, or an implementation-ready design; broader systems can be represented with Excalidraw visuals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dremonkey/agents-and-skills/draft-technical-architecture
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 dremonkey/agents-and-skills --skill draft-technical-architecture
Clone the repo
git clone --depth 1 https://github.com/dremonkey/agents-and-skills

Made for: Claude Code.

Or install agents-and-skills, the plugin that ships this one along with the rest of its 8 skills.

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 draft-technical-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/dremonkey/agents-and-skills/draft-technical-architecture.svg)](https://agentmods.dev/skills/dremonkey/agents-and-skills/draft-technical-architecture)
Your own site
<a href="https://agentmods.dev/skills/dremonkey/agents-and-skills/draft-technical-architecture"><img src="https://agentmods.dev/badge/skills/dremonkey/agents-and-skills/draft-technical-architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 674 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00674
Opus 5 $0.00035 $0.00337
Sonnet 5 $0.00014 $0.00135
Haiku 4.5 $0.00007 $0.00067

Measured 8d ago against content hash 0dfbb1da7983, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

draft-technical-architecture 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 8d 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/draft-technical-architecture/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Technical Architecture

Create practical technical specs that are easy to review and implement.

When to use this skill

Use this skill when the user asks for:

  • a new technical specification
  • component or subsystem architecture
  • an RFC-lite for a bounded change
  • implementation-ready architecture notes

This skill is optimized for small scope design work (single feature area, bounded component set).

Output goals

Every spec should be:

  • specific enough to implement
  • explicit about assumptions and tradeoffs
  • diagram-driven for faster understanding

Workflow

  1. Scope classify first

    • Confirm the request is small/bounded (component-level).
    • If scope is broad, split into bounded components and process one at a time.
  2. Gather constraints

    • Problem statement, success criteria, non-goals.
    • Technical constraints (stack, interfaces, performance, security, rollout).
    • Known unknowns and open decisions.
  3. Draft the component architecture

    • Use the template in spec-template.md.
    • Include concrete interfaces, data flow, and failure handling.
    • Prefer explicit decisions over abstract language.
  4. Add ASCII diagrams (required)

    • Use ASCII to show local architecture and behavior:
      • component boundaries
      • request/data flow
      • state transitions
      • dependency direction
    • Keep diagrams close to the section they explain.
  5. Add whole-system view (when needed)

    • If the user asks for a broader system visual, apply the excalidraw-diagram-skill.
    • Use Excalidraw for end-to-end/system-level context only.
    • Keep ASCII for component-level details even when Excalidraw is used.
  6. Finalize for implementation

    • Call out risks, mitigations, and test strategy.
    • List unresolved questions clearly.
    • Ensure acceptance criteria are verifiable.

ASCII diagram conventions

  • Prefer left-to-right flow for request pipelines.
  • Label every arrow with action or data shape where useful.
  • Use consistent naming with the prose spec.
  • Keep diagrams readable in plain markdown (no Unicode box drawing required).

Read the full file on GitHub · 97 lines

Files

What ships with it

1 file 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. 8d ago First seen · 97 lines · 70 tokens per session scan A 0dfbb1da7983

Subscribe to this mod's changes

draft-technical-architecture is a skill published in the GitHub repository dremonkey/agents-and-skills (2 stars, last pushed 24d ago), licensed MIT. It adds 70 tokens to every session and 674 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens