agentleFS
cahenesycahenesy/throughline/skills/adr-new/SKILL.md

adr-new

Skill3 starsChanged 6 months agoMITView on GitHub

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).

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. salvo8519/fairmark★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every ADR has Status: proposed | accepted | superseded by NNNN.

    line 21
  2. Distinctive:

    Never delete the old ADR. Update any design docs that referenced the old ADR's substance to point at the new one.

    line 25
  3. Very specific:

    After writing, update docs/adr/INDEX.md (create if absent): add the new row and refresh the superseded ADR's status so both rows reflect …

    line 31
  4. Distinctive:

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

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.