benchmark SKILL.md skillA
benchmark from conn-castle/agent-layer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add conn-castle/agent-layer/benchmark@git:20260902.5ca5259Pins git:20260902.5ca5259 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- conn-castle/agent-layer
- Path
internal/templates/skills-catalog/benchmark/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260902.5ca5259, committed Sep 2, 2026
- Size
- 5,000 bytes
- Repository stars
- 10
- License
- MIT
Run A/B tests of skills, instructions, agents, harnesses, and other coding-agent system changes with Agent Layer's DeltaSelect benchmark workflow. Use to select tasks, run or resume a benchmark, interpret score and cost results, or investigate why results changed.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Benchmark Help the user A/B test a change to an agent system—typically a skill, instructions, agent configuration, or harness behavior, but potentially any deliberate system change. One arm is the baseline and the other contains the change being evaluated. Match the amount of analysis and rigor the user wants; this skill does not prescribe an experimentation method. A score or cost difference always has a cause. Reporting the difference is not enough: investigate why it changed relative to the baseline and explain the root cause in simple language. Consider the whole system, including the agent, task, verifier, benchmark implementation, dependencies, environment, configuration, and cost accounting. Do not assume the benchmark is correct or stop at a symptom such as “the task failed.” Follow the evidence until the underlying cause is clear. If retained evidence cannot establish it, identify the missing evidence and gather it when possible rather than guessing. ## 1. Obtain a task selection The benchmark starts with a DeltaSelect `selection.json`. Either route is valid: - Use JSON supplied by the user. …
Read the whole file at its exact version.
How to install
mdr add conn-castle/agent-layer/benchmark@sha256:64fc75e4bb621c5aThe line at the top of this page pins the label git:20260902.5ca5259, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_oa2dxjczgojy2b6v)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 2, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5000 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
conn-castle/agent-layer · 10 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_oa2dxjczgojy2b6v GET https://markdownregistry.com/api/v1/resolve?ref=conn-castle/agent-layer/benchmark GET https://markdownregistry.com/api/v1/blob/64fc75e4bb621c5a00de72f399110ddf89f86bb64ff946b0aabe9806ff6c0611
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from conn-castle/agent-layer
Every file in conn-castle/agent-layer