
taskattest
Stop a coding agent finishing with edits outside its task. Deterministic, local, no model calls.
- tools
- 4
- transport
- STDIO
- last updated
- Nov 17, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
verify_taskJudge a task from its spec file. Returns the verdict, the evidence digest, and per-check detail
Judge a task from its spec file. Returns the verdict, the evidence digest, and per-check detail
No parameter schema in public metadata yet.
replay_evidenceRe-run a recorded manifest and report whether the digest still matches — for testing a claimed verdict instead of trusting it
Re-run a recorded manifest and report whether the digest still matches — for testing a claimed verdict instead of trusting it
No parameter schema in public metadata yet.
draft_specRead the files and propose a spec, plus a profile of every field; the draft is marked and warns until reviewed
Read the files and propose a spec, plus a profile of every field; the draft is marked and warns until reviewed
No parameter schema in public metadata yet.
describe_checksReturn the check types and a spec template, so an agent can write a spec before running one
Return the check types and a spec template, so an agent can write a spec before running one
No parameter schema in public metadata yet.
Sponsors
Readme
taskattest
Stop a coding agent from finishing with changes outside its task. taskattest is a completion gate: when the agent tries to stop, it checks what the agent changed against the files it was allowed to touch, what it produced (invented records, wrong totals, CSV and Excel), and, only if you approved them, the commands you named. A failure blocks the stop with a structured fix; the same failure three times hands over to you. Deterministic rules only — no model calls, no network, no dependencies — and every run leaves an evidence bundle you can replay.
Scope is judged from the final working tree, not by parsing tool calls, so a file written by a script or a build step counts the same as one written by Edit. Runs on Linux, macOS and Windows.
In Claude Code:
/plugin marketplace add sionjang101-create/taskattest
/plugin install taskattest@taskattest
Your own uncommitted work is recorded when the session starts, so it is never blamed on the agent. Without a definition of done in .taskattest/spec.json the gate does nothing; the define-done skill writes one with you.
Details
- Repository
- github.com/sionjang101-create/taskattest
- Categories
- AI & LLM Tools, Productivity & Office
- Package
taskattest- Transport
- STDIO
- Registry
- MCP registry, active