Verdict QA MCP server

Verdict

Your test suite is green. Verdict found a defect that had lived 4,595 days.

Verdict is a QA agent that does not fix, does not flatter, and does not forget. It measures before it judges — the harness runs your gates, hashes every line a finding cites, re-runs the guarding test at the old commit and the new one — and it keeps a memory: every run is a delta against the last, findings age, regressions rank first, and the tester's own misses are published beside its hits. The contract it runs under is immutable and hashed into every verdict; what it learns lives beside the contract, dated and auditable, and never edits it. The number above is real: FilePerms in a 4k★ Python library could not revoke a permission bit since 2014-02-07, and every one of its 625 tests was green the day Verdict filed it — the run, and the misses, are in the ledger.

/plugin marketplace add ArtJack/verdict     # Claude Code
/plugin install verdict@verdict
/verdict:run

npx skills add ArtJack/verdict              # every other coding agent

Most AI "QA agents" are a paragraph of enthusiasm with a checklist. They audit your repo from scratch every time, re-report the same 20 findings until you stop reading, call flaky tests "failures", call stale tests "failures", and end with "LGTM! 🎉".

Verdict is a Claude Code plugin built the way QA is actually practiced:

an age; every run reports NEW / STILL_OPEN / RESOLVED / REGRESSED — regressions ranked first, always.

• It remembers. A state file carries the baseline. Every finding gets a stable ID and

STALEEXPECTATION (which needs a citation proving the change was intended), BRITTLETEST, ENVIRONMENT, or FLAKY (confirmed by re-runs, quarantined with an expiry). The classification most likely to excuse a regression carries the highest evidence bar.

• A red test means something. Every failure is classified — REAL_DEFECT,

pass | pass with risks | blocked | fail — an open Blocker forces fail, blocked is a legitimate outcome, and a pass always names what was not tested.

• A verdict you can defend. Every run ends in exactly one of

QA root, and a strict-mode Bash guard closes the shell's write channels — a tester that patches what it judges isn't independent. The guard is a heuristic, not a sandbox, and the README says so.

• It never fixes your code. There is no Edit tool, a hook confines its writes to the

signed run history the model cannot forge, a track record the tester cannot edit — and a nightly audit of its own releases: 69 findings filed against itself so far, every one fixed in a tagged release with the defect pinned as a mutant the suite must kill.

• It is tested, and it tests itself. A scored eval suite with the misses published, a

Shortened. The full README is on GitHub.