A guide for creating foundational Architecture Decision Records, or ADRs—short documents that record important project decisions and their reasons.

Use it after project setup or when standardizing decision documentation, covering choices such as the technology stack, development practices, and operational needs.

It gives a new or existing project a consistent record of decisions about development, technology, and operations.

setup-adrs — Skill for Claude Code by jrjsmrtn

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/jrjsmrtn/project-orchestration-skills

agentmods

npx agentmods add skills/jrjsmrtn/project-orchestration-skills/setup-adrs

Made for: Claude Code.

Or install project-orchestration-skills, the plugin that ships this one along with the rest of its 13 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jrjsmrtn/project-orchestration-skills/setup-adrs/github.svg)](https://agentmods.dev/skills/jrjsmrtn/project-orchestration-skills/setup-adrs)

Your own site

<a href="https://agentmods.dev/skills/jrjsmrtn/project-orchestration-skills/setup-adrs"><img src="https://agentmods.dev/badge/skills/jrjsmrtn/project-orchestration-skills/setup-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jrjsmrtn/project-orchestration-skills/setup-adrs"><img src="https://agentmods.dev/badge/skills/jrjsmrtn/project-orchestration-skills/setup-adrs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,793 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00036	$0.04793
Opus 5.5	$0.00014	$0.01917
Sonnet 5.5	$0.00007	$0.00959
Haiku 4.5	$0.00004	$0.00479

Measured 3d ago against content hash d4fb183c74d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup-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 3d 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/setup-adrs/SKILL.md · 561 lines

How it starts

The opening of the file, as written. The whole thing — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Foundation ADRs

Create the foundational Architecture Decision Record (ADR) sequence for a new project.

When to Use

After running bootstrap-project skill
When establishing decision documentation for an existing project
When standardizing ADR practices across projects

Required Inputs

Project name and description (from CLAUDE.md or user)
Project type: Development, Infrastructure, or Hybrid
Technology stack decision and rationale
Development practices to adopt (can use defaults)
Operations requirements (critical for Infrastructure projects)
Project-specific constraints or requirements

Foundational ADR Framework

Every project should have these foundational ADRs:

ADR	Purpose	Scope	Critical For
ADR-0001	HOW TO DECIDE	Decision methodology	All projects
ADR-0002	HOW TO DEVELOP	Development practices	All projects
ADR-0003	WHAT TECH	Technology stack	All projects
ADR-0004	HOW TO OPERATE	Operations practices	Infrastructure, Hybrid (optional)

Note: ADR-0004 is only needed for Infrastructure and Hybrid projects. Skip it for pure development projects (libraries, CLI tools, web apps without self-hosting concerns).

Audience Traceability

ADRs serve the Contribution audience category (maintainers, contributors, future architects). They provide the "understanding-oriented" content in Diátaxis terms, explaining why decisions were made.

If a SPARK Audience Registry exists for the project, tag ADRs with the registry's identifier for the Contribution audience:

---
audience: contribution  # or the project's registry ID for maintainers/contributors
---

Pattern Reference: See AUDIENCE-DRIVEN ARTIFACTS

ADR Numbering Convention

Before creating ADRs, check for existing ones to prevent conflicts:

Read the full file on GitHub · 561 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.

3d ago Changed d4fb183c74d1
1mo ago Changed c0961431d2de
2mo ago First seen · 561 lines · 36 tokens per session scan A 0ebc387f27c3

Subscribe to this mod's changes

setup-adrs is a skill published in the GitHub repository jrjsmrtn/project-orchestration-skills (17 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 4,793 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Claude Code Planning Project Management adr plugin sprints

setup-adrs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
setup-adrsjrjsmrtn/project-orchestration-skills	Skill	17	3d ago	MIT	A	36	Claude Code
architecture-decision-record-maintainer-skillarchitecture-decision-record/architecture-decision-record	Skill	17k	8d ago	none	A	92	Claude Code, Codex
architecture-decision-record-skillarchitecture-decision-record/architecture-decision-record	Skill	17k	8d ago	none	A	108	Claude Code, Codex
c-jiradaxaur/openpaw	Skill	177	5mo ago	MIT	A	45	Claude Code, Codex
linearfurkangonel/cowrangler	Skill	1	1mo ago	MIT	A	17	Claude Code, Codex
flow-next-tracker-syncgmickel/flow-next	Skill	717	yesterday	MIT	A	44	Claude Code, Codex
taiyi-ui-designDong90/oh-my-taiyiforge	Skill	852	26d ago	MIT	A	35	Claude Code, Codex