/alcoa-guard

Lint a record / dataset / kit run for ALCOA+ data integrity (attribution, contemporaneity, completeness, accuracy, consistency). Deterministic findings + a human-judgment checklist; the report is a DRAFT, the human owns the verdict.

BOOST

s0912758806p@s0912758806p

GitHub

From plugin

agentic-sop-to-work

2094 skills4 commands

Install

> /plugin marketplace add s0912758806p/agentic-sop-to-work

How it fires

How this command gets triggered: by you, by Claude, or both.

Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/alcoa-guard

Context preview

What this command does when you run it.

Lint a record / dataset / kit run for ALCOA+ data integrity (attribution, contemporaneity, completeness, accuracy, consistency). Deterministic findings + a human-judgment checklist; the report is a DRAFT, the human owns the verdict.

Command definition

alcoa-guard.md

description: Lint a record / dataset / kit run for ALCOA+ data integrity (attribution, contemporaneity, completeness, accuracy, consistency). Deterministic findings + a human-judgment checklist; the report is a DRAFT, the human owns the verdict.
argument-hint: "<run_dir> | --record <file> --contract <.alcoa.json>"

/alcoa-guard

Invoke the alcoa-guard linter on `$ARGUMENTS`.

1. If the path is a kit run dir → `python3 -m alcoaguard.review --run-dir <dir>` (FULL). 2. If it is a record file → `python3 -m alcoaguard.review --record <file> --contract <.alcoa.json>` (DEGRADED; ask for the contract if absent). 3. With no args → run the bundled `clean` example to demonstrate.

Present the findings + human-judgment checklist verbatim, then STOP for human review.

Read it on GitHub ↗

Ships withagentic-sop-to-work

Loop Engineering — make an agent's loop produce verifiable progress, stay honest, and stay bounded, by deterministic mechanism rather than vibes.

Get the whole plugin

Stats

Python Node Linux Git Markdown

+2 tags

Mermaid Anthropic

209

Stars

Forks