A workflow for turning a software idea into an Architecture Decision Record, or ADR—a document that records important technical choices and why they were made—before implementation begins.

Use it when you know what you want built and need to investigate the project, write an approved technical decision document, and pass it into a development workflow.

It helps expose key decisions, ground them in the real code and relevant documentation, and produce a build-ready handoff.

adr — Skill for Claude Code by jasonm4130

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 jasonm4130/claude-skills --skill adr

Clone the repo

git clone --depth 1 https://github.com/jasonm4130/claude-skills

Made for: Claude Code.

Or install adr, the plugin that ships this one along with the rest of its 1 skill.

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/jasonm4130/claude-skills/adr/github.svg)](https://agentmods.dev/skills/jasonm4130/claude-skills/adr)

Your own site

<a href="https://agentmods.dev/skills/jasonm4130/claude-skills/adr"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/adr/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/jasonm4130/claude-skills/adr"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,571 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.

Model	Per session	Once invoked
Fable 5.1	$0.00138	$0.01571
Opus 5	$0.00069	$0.00785
Sonnet 5	$0.00028	$0.00314
Haiku 4.5	$0.00014	$0.00157

Measured 5d ago against content hash 29a7cea6453b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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.

The scan reads SKILL.md. This mod also ships 1 executable file (skill.test.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/adr/skills/adr/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR-Driven Development (front-end for `adr → nightshift`)

Turn an intent into one grounded, cited, build-ready ADR, then hand it to nightshift:plan's landing step. This collapses brainstorm → spec → writing-plans → nightshift into adr → nightshift for "I know what I want, build it" work.

The arc:

intent → GROUND → ADR (you approve) → plan PR → Nightshift lands it → you ratify

Stay thin. This skill is a four-phase orchestrator — prose plus the two embedded blocks below. The determinism lives in Nightshift's loop/, not here. One ADR doc, not a multi-file apparatus. For exploratory "not sure what I want yet" work use brainstorming first.

Phase 1 — Ground (scaled)

Read the real code and current external practice the change touches. Default inline; escalate to a /deep-research fan-out only when the change is novel, cross-cutting, or the user asks — a research fan-out on a one-line change is the ceremony to avoid.

State grounding: LSP (symbols/types/refs), git history, an Explore agent for breadth.
Research grounding: context7 for library docs, the cloudflare MCP for CF, a /deep-research fan-out for novel/cross-cutting work or on request — current external knowledge, not ~1-year-stale training.
Record which mode was used (inline vs research fan-out) in the ADR.

Output: a grounding brief — every claim already cited — that feeds the ADR.

Phase 2 — Author the ADR

Write docs/adr/YYYY-MM-DD-<slug>.md (dated, not numbered; create docs/adr/ if absent) using the template below.

Citation rule (hard): a codebase claim cites a file/symbol; an external claim cites a dated source; an ungrounded claim is excluded from the ADR. This makes "not stale training" auditable.
Success criteria must be checkable. Phrase each so the loop can verify it — a test that must pass, a CI signal, a concrete assertion — and mark each oracle-backed or [checker] (checker-agent-evaluable, only when no oracle exists). This block is the loop's done-oracle.
Decomposition is thin ### Task N subsections, placed LAST so task-brief extracts each cleanly — { n, title, tier, deps }-shaped, not pasted task prose.

Read the full file on GitHub · 112 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.

skill.test.mjs 1.2 KB runs code

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.

5d ago Changed · -54 lines · +18 tokens per session 29a7cea6453b
10d ago First seen · 166 lines · 120 tokens per session scan A 57f585b2a744

Subscribe to this mod's changes

adr is a skill published in the GitHub repository jasonm4130/claude-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 138 tokens to every session and 1,571 once invoked, about $0.0007 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.

Claude Code Planning Writing and docs ai-agents claude-code-plugin claude-skills plugin-marketplace

corpus

Worked examples of bad and corrected Claude Code chat output. Use when a reply is about to run long, when unsure whether a sentence is decoration or information, when a status update is forming, or when the user says the output is too long, too corporate, full of jargon, or reads like AI. Also use when writing or…

pehcastro/harness · 78 tokens

meta-tags-optimizer

Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…

nowork-studio/notfair-plugin · 91 tokens

google-ads-audit

Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…

nowork-studio/notfair-plugin · 86 tokens

sxo

Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…

nowork-studio/notfair-plugin · 235 tokens

critical-code-reviewer

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.

posit-dev/skills · 67 tokens

shiny-bslib

Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…

posit-dev/skills · 107 tokens