hoangsonww/claude-code-agent-monitor · plugins/ccam-insights/skills/benchmark/SKILL.md

benchmark skillA

benchmark is agent-read markdown (skill) from hoangsonww/claude-code-agent-monitor: Benchmark one session (or a small recent set) against the rolling average using Agent Monitor data — cost, total tokens, tool count, and workflow complexity score — and report where each metric lands as a percentile of the population. Tells you whether a session was normal, cheap, or an outlier. Use when judging whether a session was typical or out of band..

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 hoangsonww/claude-code-agent-monitor/benchmark@git:20260804.9eab0d7
Exact content
mdr add hoangsonww/claude-code-agent-monitor/benchmark@sha256:0c41d3188c78153a

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_j73uytujgxuzfc2a.svg)](https://markdownregistry.com/a/art_j73uytujgxuzfc2a)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260804.9eab0d7 latest2026-08-04 9eab0d7 3,376 BA view · diff
git:20260625.879bbc22026-06-25 879bbc2 3,360 BB 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 (3376 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

hoangsonww/claude-code-agent-monitor · 1,007 stars · license MIT · pushed 2026-09-13 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_j73uytujgxuzfc2a
GET https://markdownregistry.com/api/v1/resolve?ref=hoangsonww/claude-code-agent-monitor/benchmark
GET https://markdownregistry.com/api/v1/blob/0c41d3188c78153a1bc4a4db56213a615365aabec4397a07ff5e2def15b6a092

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