Skip to content
Back to skills

Adr New

ASecurity

Create a new Architecture Decision Record with append-only, status-gated supersession, and update the ADR index. Invoke with /adr-new, or let /tdd-author invoke it on approval of an ADR action (this skill stays model-invocable for that reason).

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 6, 2026
ai-agents

Security analysis

A100/100

Scanned October 6, 2026

npx -y skills add cahenesy/throughline --skill adr-new --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adr New?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Adr New
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/cahenesy-adr-new/badge)](https://www.skillsdirectory.com/skills/cahenesy-adr-new)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: adr-new
description: Create a new Architecture Decision Record with append-only, status-gated supersession, and update the ADR index. Invoke with /adr-new, or let /tdd-author invoke it on approval of an ADR action (this skill stays model-invocable for that reason).
---

# New ADR

Record a durable architectural decision or established pattern. ADRs are the
sparse, forward-feeding memory loaded into every future call to /tdd-author
so keep the bar high and the set small.

## Rules — enforce strictly

- APPEND-ONLY ON SUBSTANCE. Once an ADR is `accepted` (or built upon), its
  Context/Decision/Consequences are historical record. Light editorial touch-ups
  are fine — typos, a broken link, flipping `proposed`→`accepted`, marking
  `superseded by`. Anything that changes the SUBSTANCE of the decision is a new
  superseding ADR, never an edit. Rewriting the body destroys the record of what
  was decided and why at the time.
- Assign the next zero-padded number: highest existing in `docs/adr/` + 1.
- Every ADR has Status: `proposed` | `accepted` | `superseded by NNNN`.
- To reverse or replace a prior decision: create a NEW ADR with
  `Supersedes: NNNN` that captures the new context, decision, and consequences
  in FULL; then change ONLY the old ADR's Status line to `superseded by <new>`.
  Never delete the old ADR. Update any design docs that referenced the old ADR's
  substance to point at the new one.
- Challenging an accepted decision is encouraged when new information surfaces (a
  dependency's license, a competitor's architecture, a UX constraint) — say so
  plainly and supersede. Changing a decision early is far cheaper than discovering
  it was wrong after weeks of building on it. ADRs are accepted, not immutable.
- After writing, update `docs/adr/INDEX.md` (create if absent): add the new row
  and refresh the superseded ADR's status so both rows reflect the new state.

## ADR template

```
# NNNN. <title>
Status: accepted
Date: <YYYY-MM-DD>
Scope: <domain — used by the index and by TDD relevance matching>
Supersedes: <NNNN, if applicable>

## Context
## Decision
## Consequences
```

## Index format — docs/adr/INDEX.md

```
# ADR Index
> Only `accepted` ADRs are binding constraints for new TDDs.

| #    | Title   | Status   | Scope   |
|------|---------|----------|---------|
| 0001 | <title> | accepted | <scope> |
```

Keep each row to one line so the whole index stays cheap to keep in context.

## Commits
This skill only WRITES files (the ADR and the index). It does not commit or
branch. ADRs are committed by the design phase (`/tdd-author`) together with the
TDD set, so they travel in the design PR that justifies them.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.