settings
Skill13 starsChanged 4 months agoMITView on GitHub
Show and change adr-kit settings: LLM backend, judge-by-default, hooks, the status-history signer, guardian cadence. Use to inspect where a value comes from or to change one.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- buildomator/buildomatortheir own version, first seen Nov 4, 2026
- tjmode/koovitheir own version, first seen Nov 1, 2026
- aibtcdev/skillstheir own version, first seen Oct 26, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Oct 19, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
- wfukatsu/slide-forgetheir own version, first seen Sep 17, 2026
Used with
Projects with it also use help.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkillhelp
Entry point for the MedImageInsight plugin, covering the getting-started walkthrough, how the skills work, what MI2 is, and troubleshooting.
Also in 3 projects that use this
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- buildomator/buildomator★ 102same name
- crisandrews/ClawCode★ 64same name
- liamcain/obsidian-dev-skills★ 16same name
- aibtcdev/skills★ 11same name
- wfukatsu/slide-forge★ 5same name
- MaGe1993/Claude-Code-Base-Harness★ 1same name
- tjmode/koovi★ 1same name
- venus2099/codex-game-studios★ 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 repository19 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Every row carries its provenance — project, machine-local, default, or an environment override.
- Very specific: line 31
Add --all for every key the schema knows, --format json for a machine reading, --list for just the key names.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
adr-kit settings
Reply in the language the user writes in; default to English. Keep command output, identifiers, paths, and ADR file content unchanged.
$ARGUMENTS may name a key to show, or a key=value to set. Empty shows
everything with its provenance.
One place for every knob. Before this existed a user changed settings in three
disjoint places and one text editor, and two things were simply unreachable:
judge.llm_enabled could be switched on by a shipped writer but never off, and
the status-history signer had nowhere to live that anyone would find.
Show
python3 "$ADR_KIT/bin/adr-settings" --adr-dir docs/adrEvery row carries its provenance — project, machine-local, default, or an environment override. That is the column that answers the question a settings screen exists for: not "what is this set to" but "why is it set to that".
Add --all for every key the schema knows, --format json for a machine
reading, --list for just the key names.
Change
python3 "$ADR_KIT/bin/adr-settings" --adr-dir docs/adr --set judge.llm_enabled=false
python3 "$ADR_KIT/bin/adr-settings" --adr-dir docs/adr --unset guardian.enabledValues are typed against the schema before they land: --set guardian.enabled=maybe
is refused rather than stored as a truthy string, and a refused write leaves no
file behind.
Which file a setting lands in, and why it matters
| Scope | File | Contains |
| project | docs/adr/.adr-kit.json (tracked) | team decisions: judge behaviour, guardian cadence, retrieval limits |
| machine-local | docs/adr/.adr-kit.local.json (gitignored) | personal or machine facts: lifecycle.signer, judge.host_client |
The command routes each write itself and says where it landed. The split is not bookkeeping: a signer written to the tracked file would put one person's name on every teammate's acceptance, which is a false attribution rather than a missing one. And a host client is a fact about one machine, not a decision about the project.
Settings that live elsewhere on purpose
- The signer can also be set through
bin/adr signer --set "User: <name>", which additionally offersgit config user.nameas a proposal and can audit existing history for entries with no human actor. - Hook installation is
/adr-kit:install-hooks, because installing a hook writes files outside the config and needs its own consent. - The LLM backend can also be set through
adr-judge --set-backend, which validates the choice against the live registry.
This command shows all of them; where another surface does more than write a value, it says so rather than duplicating the work.
What is never shown
A credential is reported as a boolean about the environment — whether a key is present, never the key. A settings screen needs to know that the environment is configured; it does not need the secret to say so.
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
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.