writing-adrs

writing-adrs is a skill for Claude Code from dork-labs/dorkos. It costs 30 tokens per session (1,958 once invoked), scanned A, original, MIT.

A guide for writing Architecture Decision Records (ADRs), short notes that record important technical choices and why they were made.

In plain words
What is it for?
Use it to create ADRs, turn specifications into decision records, or check whether existing ADRs clearly explain their context, options, and outcomes.
Why use it?
It keeps the reasoning behind lasting decisions available to future developers and coding agents, instead of leaving them to guess.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

Part of the flow plugin — 32 skills, 43 commands, 5 agents, 4 hooks shipped together

Good fit Use it to create ADRs, turn specifications into decision records, or check whether existing ADRs clearly explain their context, options, and outcomes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dork-labs/dorkos/writing-adrs
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 dork-labs/dorkos --skill writing-adrs
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 32 skills, 43 commands, 5 agents, 4 hooks.

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 writing-adrs

README.md
[![agentmods](https://agentmods.dev/badge/skills/dork-labs/dorkos/writing-adrs/github.svg)](https://agentmods.dev/skills/dork-labs/dorkos/writing-adrs)
Your own site
<a href="https://agentmods.dev/skills/dork-labs/dorkos/writing-adrs"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/writing-adrs/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 writing-adrs

Your own site · 80×15
<a href="https://agentmods.dev/skills/dork-labs/dorkos/writing-adrs"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/writing-adrs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,958 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 $0.00030 $0.01958
Opus 5 $0.00015 $0.00979
Sonnet 5 $0.00006 $0.00392
Haiku 4.5 $0.00003 $0.00196

Measured 10d ago against content hash 17cfc9789cd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

writing-adrs 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 10d 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.

.agents/skills/writing-adrs/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Architecture Decision Records

Overview

Architecture Decision Records (ADRs) capture significant technical decisions in a concise, standardized format. They answer "why did we do this?" for future developers and AI agents. DorkOS ADRs live in decisions/ with a manifest.json index.

When to Write an ADR

Write an ADR when a decision:

  • Chooses between alternatives — "We picked X over Y because..."
  • Adopts a pattern or technology — New library, architecture pattern, data model
  • Has lasting consequences — Affects how future features are built
  • Would surprise a new team member — Non-obvious choices that need explanation

When NOT to Write an ADR

Skip ADRs for:

  • Trivial implementation details — Variable naming, file placement within an established structure
  • Obvious choices — Using TypeScript in a TypeScript project
  • Temporary decisions — Workarounds that will be replaced soon
  • Single-feature scope — Decisions that only affect one spec with no project-wide impact

Writing Guidelines

Context (2-5 sentences)

Focus on the problem, not the solution. What situation existed? What forces were at play?

  • Good: "DorkOS runs as both a standalone web app and an Obsidian plugin. The Obsidian plugin cannot make HTTP requests to localhost, so the client needs a way to communicate with the server that works in both environments."
  • Bad: "We needed an architecture." (Too vague)
  • Bad: A full page of background. (Too long — that belongs in the spec)

Decision (2-5 sentences)

State what was decided in active voice. Start with "We will..."

  • Good: "We will use a Transport interface that abstracts the communication layer. HttpTransport handles standalone mode via REST/SSE. DirectTransport handles Obsidian mode via in-process function calls."
  • Bad: "The transport pattern was implemented." (Passive, vague)

Consequences

List concrete positives and negatives. Every decision has trade-offs — if you can't list a negative, think harder.

Read the full file on GitHub · 146 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.

  1. 10d ago First seen · 146 lines · 30 tokens per session scan A 17cfc9789cd6

Subscribe to this mod's changes

writing-adrs is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,958 once invoked, about $0.0002 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.