1. Conduid
  2. Science
  3. Mini Antemortem CLI
MCP server · Science

Mini Antemortem CLI

by · github.com/hibou04-ops/mini-antemortem-cli

Deterministic, offline linter that catches silent traps in your prompt-eval setup — train/test leakage, judge bias, homogeneous variants — before they fake a passing score. 11 trap rules.

Unclaimed evalslinterllmllm-evaluationmcpprompt-engineeringpythonstatic-analysis
InstallView source
34Low

Scored a month ago · breakdown

About Mini Antemortem CLI

Mini Antemortem CLI is an MCP server published by hibou04-ops in the Science category: deterministic, offline linter that catches silent traps in your prompt-eval setup — train/test leakage, judge bias, homogeneous variants — before they fake a passing score. 11 trap rules.

The repository has 1 stars and 0 forks, with the last commit 10 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/hibou04-ops/mini-antemortem-cli

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Mini Antemortem CLI

Powered by Claude · Grounded in docs

I know everything about Mini Antemortem CLI. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.10.1mini-antemortem-cli 0.10.1 — Omega Aile compatibility patch · 7 Oct 2026Bound FastMCP to SDK >=1,<2. Add an installed offline trap registry path and analytical findings handoff. Align README and release checklist with the existing manual workflow_dispatch/release_tag publish path. Omega Aile — Quiet precision.…
v0.10.0v0.10.0 — JSON output, severity CI gate, new trap rules, claim-drift fix + distribution README · 12 Jun 2026mini-antemortem-cli 0.10.0 A deterministic linter that catches the silent traps in your prompt-eval setup — train/test leakage, judge bias, homogeneous variants — before they fake a passing score. Works with `omegaprompt`; useful…
v0.9.0mini-antemortem-cli 0.9.0 · 8 Jun 2026mini-antemortem-cli 0.9.0 Analytical-preflight CLI — feature elevation + promotion to Beta. Additive (no contract change) Verdict line (C1): text output now leads with a grep-friendly `Summary: <STATUS> [<sev>] - N…
v0.8.0v0.8.0: false-positive audit corpus + CI gate · 28 May 2026Highlights Quantified analytical-preflight false-positive rate for the first time and wired it into CI. The classifier was previously known to be 100% deterministic but the FP rate against benign inputs was unmeasured — this release closes…
v0.7.0v0.7.0 — cb=3 refresh stuck PyPI badge · 22 May 2026Why PyPI 0.6.0 page is permanently stuck displaying `v0.5.0` on its PyPI badge — its embedded README baked in `?cb=1`, which Cloudflare HIT-cached on shields.io while it was serving the then-current 0.5.0 response. PyPI per-version…
Questions

About Mini Antemortem CLI

How do I install Mini Antemortem CLI?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Mini Antemortem CLI safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Mini Antemortem CLI still maintained?

Yes — the latest release is v0.10.1 (7 Oct 2026), and the last commit was 10 days ago. The repository has 1 stars.