adr-creator

adr-creator is a skill for Claude Code, Codex from wufunc/nova. It costs 72 tokens per session (961 once invoked), scanned A, original, MIT.

A writer for Architecture Decision Records, or ADRs: short files that document important technical choices and their reasons. It is called by the memory skill when an architectural decision should be recorded.

In plain words
What is it for?
Use it to create numbered ADR files with summaries, tags, affected modules, dates, and decision details.
Why use it?
It keeps important design decisions searchable and consistent without asking the writer to decide when an ADR is needed.

Skill for Claude CodeCodex

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/wufunc/nova/adr-creator
Any agent
npx skills add wufunc/nova --skill adr-creator
Clone the repo
git clone --depth 1 https://github.com/wufunc/nova

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 961 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 $0.00072 $0.00961
Opus 5 $0.00036 $0.00481
Sonnet 5 $0.00014 $0.00192
Haiku 4.5 $0.00007 $0.00096

Measured 3d ago against content hash 3ab79ac90080, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-creator 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-creator/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Creator

Overview

Pure writer skill that creates Architecture Decision Records. Always invoked by the memory skill, never directly for decision-making. Receives the session context where architectural decisions were made and generates properly formatted ADR files.

Workflow

Step 1: Determine ADR Number

# List existing ADRs to find the highest number
Glob pattern: .nova/memory/adr/[0-9]*.md

# Use next sequential three-digit number (001, 002, 003...)

Step 2: Determine Memory Tag

# Find the latest mem tag to determine next number
git tag -l 'mem/*' --sort=-version:refname | head -1

# Next tag: mem/NNN (increment by 1)
# If no tags exist, use mem/001

If the memory skill has already provided a tag name (because a DevLog is also being created in this session), use that same tag.

Step 3: Generate ADR Content

Analyze the conversation to extract the architectural decision. Follow the format in references/adr-format.md.

Structure:

---
tags: [tag1, tag2, tag3]
modules: [path/to/module1, path/to/module2]
summary: "One-line summary of the decision for Grep-based retrieval"
tag: mem/NNN
---

# ADR NNN: Concise Decision Title

## Date
YYYY-MM-DD HH:mm

## Background
- Problem description
- Why a decision was needed
- Technical constraints
- Alternative approaches considered

## Decision
- Chosen approach
- Key implementation points
- Design rationale (why this approach, why not others)

## Consequences
### Advantages
- Positive impacts

### Disadvantages
- Negative impacts and trade-offs

### Risk Mitigation (optional)
- How to reduce negative impacts

## Related Decisions
- ADR XXX: Reference to related decisions

Content Guidelines:

  1. Title (max 10 words): Concise description of the decision
  2. YAML Frontmatter: Must include tags, modules, summary, tag (for Grep-based retrieval)
  3. Background: Explain the "why", list alternatives considered
  4. Decision: State what was chosen and justify why
  5. Consequences: Be honest about both advantages and disadvantages
  6. Related Decisions: Reference other ADRs if applicable (use "None" if none)

Read the full file on GitHub · 138 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 · 138 lines · 72 tokens per session scan A 3ab79ac90080

Subscribe to this mod's changes

adr-creator is a skill published in the GitHub repository wufunc/nova (2 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 961 once invoked, about $0.0004 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.