# Settings

> Show and change adr-kit settings with the provenance of each value, routing team decisions and personal facts to their own files.

- Skill: `rvdbreemen/settings-3` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rvdbreemen/settings-3`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rvdbreemen/settings-3/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT
- Author: rvdbreemen (https://skillmd.com/u/rvdbreemen)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rvdbreemen/settings-3

---


<!-- Generated by scripts/build-client-adapters.py from clients/workflows.json; schema v1; client github-copilot-cli. -->
# Show or change a setting

Select `adr-kit:settings` from `/skills`, or ask Copilot to use the `settings` ADR Kit skill.
Resolve `<plugin-root>` from this installed skill. Use only bundled,
local ADR Kit tools and follow this canonical workflow:

1. Run `python <plugin-root>/bin/adr-settings --adr-dir docs/adr` and report every value with its provenance: project, machine-local, environment override, or code default.
2. Name the environment override explicitly when one is present, because a config value that is not taking effect is the question a settings screen exists to answer.
3. On a change, run `--set KEY=VALUE`; the value is typed and validated against the schema before it lands, and a refused write leaves no file behind.
4. State which file the write landed in: team decisions in the tracked config, personal or machine-specific facts in the gitignored local one.
5. For backend selection prefer `adr-judge --set-backend`, which validates the choice against the live registry; for hook installation defer to install-hooks, which needs its own consent.
6. Never print a credential; report only whether the environment carries one.

Do not contact another model or mutate user-owned instructions.