adr-quality

A skill for creating, reviewing, improving, and maintaining architectural decision records, or ADRs. An ADR is a short document that records an important technical choice and why the team made it.

In plain words
What is it for?
Use it to check ADR titles and content, review existing decisions, validate ADR quality, and improve decision records.
Why use it?
It helps ensure decisions are understandable, complete, concise, well explained, and still accurate for future readers.

Skill for Claude CodeCodex

Part of the adr plugin — 12 skills, 7 commands, 3 agents shipped together

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/zircote-plugins/adr/adr-quality
Any agent
npx skills add zircote-plugins/adr --skill adr-quality
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/adr

Made for: Claude Code, Codex.

Or install adr, the plugin that ships this one along with the rest of its 12 skills, 7 commands, 3 agents.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,518 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 $0.00055 $0.01518
Opus 5 $0.00028 $0.00759
Sonnet 5 $0.00011 $0.00304
Haiku 4.5 $0.00006 $0.00152

Measured 3d ago against content hash 8fe1cbf658c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-quality 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/adr-quality/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Quality

This skill provides guidance on creating, evaluating, and maintaining high-quality Architectural Decision Records. Quality ADRs are clear, complete, and useful for future readers.

Quality Criteria

The 5 C's of ADR Quality

Criterion Definition Questions to Ask
Clear Easy to understand Can a new team member understand this?
Complete All relevant information Are all sections filled out meaningfully?
Concise No unnecessary content Is every sentence adding value?
Contextual Sufficient background Is the "why" clear?
Current Reflects actual state Is the status accurate? Are links valid?

Essential Quality Checks

Title Quality

Good titles are:

  • Specific and searchable
  • Action-oriented (verb + noun)
  • Not too broad or too narrow
Quality Example
Good "Use PostgreSQL for primary data storage"
Good "Adopt event-driven architecture for order processing"
Bad "Database"
Bad "Technical decision about which database to use for storing user data"

Context Quality

Context should answer:

  • What problem are we solving?
  • What is the current state?
  • What constraints exist?
  • Who are the stakeholders?

Good context example:

Our e-commerce platform needs to handle user authentication across
mobile and web applications. Currently, authentication is handled
separately in each app, leading to inconsistent security and duplicate
code. We have 50,000 active users and expect 10x growth in 2 years.
The team has experience with OAuth but not SAML.

Decision Drivers Quality

Drivers should be:

  • Specific (not "performance" but "sub-100ms response time")
  • Prioritized or weighted
  • Traceable to stakeholder needs
  • Testable or measurable

Options Quality

Each option should have:

  • Clear description
  • Genuine consideration (not straw man)
  • Fair pros and cons analysis
  • Sufficient detail for comparison

Read the full file on GitHub · 232 lines

Files

What ships with it

2 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. 3d ago First seen · 232 lines · 55 tokens per session scan A 8fe1cbf658c9

Subscribe to this mod's changes

adr-quality is a skill published in the GitHub repository zircote-plugins/adr (5 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 1,518 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

bootstrap

Scaffold or retrofit documentation-led conventions (AGENTS.md, CLAUDE.md, CONVENTIONS.md, ADR catalogue, plan/ queue, agent/ coordination) into a repo. Use when the user asks to "set up conventions", "bootstrap ADRs", "scaffold the documentation-led layout", "add AGENTS.md and a plan queue", or invokes /bootstrap.…

EvolveHQ/docflow · 118 tokens

agent-wave

Orchestrate a wave of parallel agents over the plan/todo queue in a documentation-led repo — asks how many agents, the budget (items/waves, with hours as a soft cap), and whether to checkpoint after each wave or run continuously. Spawns isolated worktree subagents, assigns one queue item each, collects results. Use…

EvolveHQ/docflow · 105 tokens

audit

Audit a documentation-led repo against its own conventions — contiguous ADR numbering, INDEX sync, plan/ coverage, required sections, status validity, cross-reference resolution, language mandate, ADR-privacy leaks into user-visible code, cross-worktree collisions (duplicate numbers, duplicate plan ownership, same ADR…

EvolveHQ/docflow · 145 tokens

new-adr

Author a new ADR — record a DECISION (what the system must do, or how it is built) in a documentation-led repo. Picks the next contiguous number, chooses the shape (capability vs technology), fills the template, sets status Proposed, regenerates INDEX, updates domain READMEs, handles supersede/deprecate linkage…

EvolveHQ/docflow · 147 tokens

add-convention

Assess and add a CONVENTION (a reusable rule, practice, or naming/process standard) to a documentation-led repo — decides FIRST whether it is worth codifying at all, then routes it to the right home (AGENTS.md hard rule, CONVENTIONS.md guidance, GLOSSARY term, or to /new-adr if it is really a one-off decision). Pushes…

EvolveHQ/docflow · 150 tokens

brainstorm

Decompose a problem, feature, or goal into candidate ADRs and plan items for a documentation-led repo — one decision per ADR, dependency edges, suggested ordering. Proposes drafts for review and writes nothing until approved. Use when the user says "brainstorm ADRs", "break this down into decisions", "what ADRs do we…

EvolveHQ/docflow · 87 tokens