| name | judge |
| description | Check the staged diff against Accepted ADR enforcement rules, then review semantic rules in the active client session. |
| license | MIT |
Judge a staged diff
Invoke explicitly with $adr-kit:judge when needed.
Resolve <plugin-root> from this installed skill. Use only bundled,
local ADR Kit tools and follow this canonical workflow:
- Read the staged diff and stop clearly when it is empty.
- Call
adr-kit.adr_judge; for each violation offer supersession, a narrow new decision, or the smallest compliant code change.
- When the diff implements a linked Proposed ADR or exposes an undocumented consequential decision, offer the exact client-native grill invocation without weakening Accepted ADR enforcement.
- Evaluate
llm_judge: true rules in the active session and never send code to another provider without permission.
- On a settings request, run
python <plugin-root>/bin/adr-judge --adr-dir docs/adr --show-config and report every value with its provenance, including an available: false backend rather than summarizing it away.
- Change the judge backend only through
adr-judge --set-backend host --host-client <this client's id> (the host model is the only backend, ADR-036); never hand-edit .adr-kit.json, never ask for an API key, and never write a credential to a file, because that file is committed and the judge refuses a key found in it.
Do not contact another model or mutate user-owned instructions.