adr

adr is a skill for Claude Code from addit-digital/addit-harness. It costs 67 tokens per session (1,454 once invoked), scanned A, original, MIT.

A skill that creates an Architecture Decision Record, or ADR: a durable note in the code repository explaining an important technical choice and its consequences. It uses the MADR format, a structured style for writing these records.

In plain words
What is it for?
Use it for framework, database, API, data-model, integration, security, architectural-pattern, and other significant technical decisions.
Why use it?
It keeps the reasons behind difficult or hard-to-reverse decisions available to future maintainers, not just the final choice.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the addit-harness plugin — 6 skills, 6 commands, 14 agents, 1 hook 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/addit-digital/addit-harness/adr
Any agent
npx skills add addit-digital/addit-harness --skill adr
Clone the repo
git clone --depth 1 https://github.com/addit-digital/addit-harness

Made for: Claude Code.

Or install addit-harness, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 14 agents, 1 hook.

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 adr

README.md
[![agentmods](https://agentmods.dev/badge/skills/addit-digital/addit-harness/adr.svg)](https://agentmods.dev/skills/addit-digital/addit-harness/adr)
Your own site
<a href="https://agentmods.dev/skills/addit-digital/addit-harness/adr"><img src="https://agentmods.dev/badge/skills/addit-digital/addit-harness/adr.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,454 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 5.1 $0.00067 $0.01454
Opus 5 $0.00034 $0.00727
Sonnet 5 $0.00013 $0.00291
Haiku 4.5 $0.00007 $0.00145

Measured 5d ago against content hash 54eaa21e2917, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

adr 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 5d 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/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Decision Record (ADR) — MADR format

Capture a significant architectural/technical decision as a durable, structured record in MADR 4.0 format (Markdown Any Decision Records), stored in version control next to the code so future readers understand why, not just what.

Sources / further reading:

When to write one

ADR-worthy = significant and hard to reverse: technology/framework/database choice, API or integration style, data model, architectural pattern (monolith vs services, sync vs event-driven), security approach, or a notable trade-off. Skip trivial, easily-reversed choices.

Choosing minimal vs full

  • Minimal (default): smaller/medium decisions — Context & Problem, Considered Options, Decision Outcome (+ Consequences).
  • Full: weighty decisions with several real alternatives — adds Decision Drivers, per-option Pros and Cons, Confirmation, and More Information.
  • Honor --full/--minimal if given; otherwise pick by decision weight.

Procedure

  1. Locate/initialize the store. Use docs/adr/. If it doesn't exist, create it and a docs/adr/README.md index. If the repo already has an ADR location or template, follow that instead. Optionally seed the meta-ADR 0001-record-architecture-decisions.md (records the decision to use ADRs).
  2. Assign the next number. Scan docs/adr/ for the highest NNNN, increment; 4-digit zero-padded starting at 0001.
  3. Gather context. From the conversation/code extract: the problem and why now, decision drivers/forces, the alternatives considered, the chosen option, and consequences (good and bad). Ask the user only for what you can't infer — especially alternatives rejected and why, the most valuable part.
  4. Write docs/adr/NNNN-kebab-case-title.md using the matching template below. When the decision involves architecture or flow, embed a mermaid diagram (component graph/flowchart and/or sequenceDiagram) in Context and Problem Statement and/or per option — ADRs live as files / on GitHub, so mermaid renders. Skip it for non-structural decisions.
  5. Update the index docs/adr/README.md with a row: number, title (link), status, date.
  6. Report the path and a one-line summary. Don't commit unless asked.

Read the full file on GitHub · 172 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. 5d ago First seen · 172 lines · 67 tokens per session scan A 54eaa21e2917

Subscribe to this mod's changes

adr is a skill published in the GitHub repository addit-digital/addit-harness (3 stars, last pushed 13d ago), licensed MIT. It adds 67 tokens to every session and 1,454 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

go

Use when writing, reviewing, testing, or shipping Go code and HTTP services: idioms, %w error wrapping, goroutine/context/errgroup concurrency, net/http 1.22 routing, log/slog, project layout, table-driven tests, Go hardening. NOT language-agnostic threat modeling (that is secure-coding), NOT Dockerfile/CI shipping…

ericrisco/rsc-harness · 86 tokens

ccg-annotate

AI-driven annotation workflow for adding structured metadata to code. Annotations are indexed and searchable via FTS.

tae2089/code-context-graph · 26 tokens

ccg-namespace

Isolate read-only CCG search, documentation discovery, and analysis by namespace. Use when working across multiple repositories or services, preventing cross-project graph leakage, federating supported reads, or traversing materialized cross-namespace references. Do not use for graph writes or scoped updates; the user…

tae2089/code-context-graph · 73 tokens

ccg-docs

Generate Markdown documentation from code graphs, build RAG indexes for AI consumption, and lint documentation quality.

tae2089/code-context-graph · 23 tokens

ccg-analyze

Explicit-only deep analysis of algorithms, feature pipelines, and code relationships with CCG impact radius, bounded flow tracing, callers/callees, git-diff risk, affected stored flows, and cross-namespace references. Use only when the user explicitly names the ccg-analyze skill in the current request. Do not invoke…

tae2089/code-context-graph · 87 tokens

ccg-build

Explicit-only graph ingestion for building, updating, migrating, and postprocessing code-context-graph graphs from source visible to the CCG runtime. Use only when the user explicitly names the ccg-build skill in the current request. Do not invoke merely because a graph is missing or stale, annotations need…

tae2089/code-context-graph · 76 tokens