sionjang101-create avatar

taskattest

sionjang101-create/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 tools

Public 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.


View the full README on GitHub

Details

Repository
github.com/sionjang101-create/taskattest
Categories
AI & LLM Tools, Productivity & Office
Package
taskattest
Transport
STDIO
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1slashml-ai avatarSlashML (/ ml) Embodied Robotics Trajectory Memoryslashml-ai/slashml-roboticsSub-millisecond 7-DoF trajectory episode memory and kinematic safety gates for robotics.0stars
2smoke711711 avatarAshfields MCP Serversmoke711711/ashfields-mcp-serverBurn $ASH to mint on-chain NFTs on Ethereum. No browser. Two agent tool calls.0stars
3sooda-ai avatarSooda MCPsooda-ai/sooda-mcpAI agent relay — message business agents across company boundaries via A2A protocol0stars
4sprtxbabe avatarSprtx Mcpsprtxbabe/sprtx-mcpAgent-native sports token network. 1,435 tokens across 98 sports, 9 global regions.0stars
5srotzin avatarExecute Intentsrotzin/hive-executeIntent execution engine for autonomous agent task routing0stars
6srotzin avatarHive Aml Screensrotzin/hive-mcp-aml-screenReal-time AML and sanctions screening for agent-to-agent transactions0stars