monte-carlo-data/mc-agent-toolkit · skills/troubleshoot-agent-traces/SKILL.md

monte-carlo-troubleshoot-agent-traces skillA

monte-carlo-troubleshoot-agent-traces is agent-read markdown (skill) from monte-carlo-data/mc-agent-toolkit: Troubleshoots Monte Carlo AI agent alerts and traces — eval score drops, latency/token spikes, trajectory and validation breaches. Not for data incidents (monte-carlo-analyze-root-cause) or monitor creation (monte-carlo-monitoring-advisor)..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add monte-carlo-data/mc-agent-toolkit/monte-carlo-troubleshoot-agent-traces@git:20260726.3aef355
Exact content
mdr add monte-carlo-data/mc-agent-toolkit/monte-carlo-troubleshoot-agent-traces@sha256:4ea165f23ca2cc6c

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_dzyeicb6a27kj3ms.svg)](https://markdownregistry.com/a/art_dzyeicb6a27kj3ms)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260726.3aef355 latest2026-07-26 3aef355 17,402 BA view · diff
git:20260720.70c5d122026-07-20 70c5d12 17,187 BA view · diff
git:20260719.0b4edc32026-07-19 0b4edc3 17,179 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (17402 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

monte-carlo-data/mc-agent-toolkit · 91 stars · license Apache-2.0 · pushed 2026-09-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dzyeicb6a27kj3ms
GET https://markdownregistry.com/api/v1/resolve?ref=monte-carlo-data/mc-agent-toolkit/monte-carlo-troubleshoot-agent-traces
GET https://markdownregistry.com/api/v1/blob/4ea165f23ca2cc6ce8056344a847c1435431fbfe3ca0f8ac88d639139191d9bc

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.