An open-source accountability queue for AI coding agents. The agent that does the work can't close it — a second agent verifies it against ground truth first.
works with Claude Code · Cursor · any MCP agent — Postgres + MCP server · MIT
AI agents will happily do 80% of a task, declare victory, and quietly break something else on the way out.
Coretexa is the queue that catches it.
The last, hard 20% — edge cases, cleanup, the thing that actually mattered — gets rounded up to "complete" and handed back.
The change that passed its own test quietly regressed a file three directories over. Nobody looked, because the agent said it was fine.
The thing that did the work is the thing that decided the work was good. That's not review — that's a rubber stamp with extra steps.
pending → claimed → done → verified → closed, with a blocked branch. A token travels the happy path; the self-close attempt forks and is rejected.
The requested behavior exists and works — not an approximation of it.
No adjacent regression. What passed before still passes.
Internally coherent — names, types, contracts, and docs agree.
The full task — not the easy 80% with the hard part deferred.
A different actor confirmed gates 1–4 against reality. Not the doer.
No-self-close isn't a code-review culture you hope people follow. It's an invariant. The server checks the actor id on every close, and refuses when the verifier is the same identity that claimed the ticket.
Enforced by the server, not by convention.
Something that passed before now fails on verify. The system files a linked follow-up ticket and escalates its priority. The agent can't suppress it — the correction is the system's, not the doer's.
Every ticket carries its parent. So you can measure how many generations of fix-broke-something a change took to settle. A deep lineage is a map straight to the fragile parts of your codebase.
origin ∈ {manual, spawned, correction, regression} · linked by parent_id. This subtree settled in 3 generations — that's a fragile area worth a human's attention.
Not a framework looking for a user — a habit, extracted.
Built by one developer who ran it 100+ tickets deep. 14 MCP tools; a 29-test suite runs the full lifecycle against in-memory Postgres.
Postgres owns the queue. One file, one command.
psql < schema.sqlRegister the server twice — once as the doer, once as the verifier. Two distinct actor ids is the whole point.
Run /work-queue to claim and do. Then /verify-queue from a second session to check and close.
MIT licensed. A Postgres schema and a reference MCP server that works with any MCP agent. Take it, run it, break it, send it back better.
early, solo, and MIT — PRs welcome (they go through the queue).