AGENTS.md@resources/personal-ai-benchmark-kit/unpacked/personal_benchmark_skill/personal-benchmarkA
AGENTS.md@resources/personal-ai-benchmark-kit/unpacked/personal_benchmark_skill/personal-benchmark from earlyaidopters/gumroad-resources is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add earlyaidopters/gumroad-resources/resources/personal-ai-benchmark-kit/unpacked/personal_benchmark_skill/personal-benchmark/AGENTS.md@git:20260810.9572c5cPins git:20260810.9572c5c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- earlyaidopters/gumroad-resources
- Path
resources/personal-ai-benchmark-kit/unpacked/personal_benchmark_skill/personal-benchmark/AGENTS.md- Versions recorded
- 1
- Latest version
- git:20260810.9572c5c, committed Aug 10, 2026
- Size
- 6,278 bytes
- Repository stars
- 48
- License
- none declared
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
# AGENTS.md, read this first if you are an AI agent
This repo is a Claude Code skill called `/benchmark`. It mines a user's own Claude
Code conversation history into a frozen personal eval pack, replays that pack
headlessly against any Claude model or effort level, blind-judges the results, and
produces a verdict, an HTML report, and a share card.
## Which file do you need?
| You are... | Read |
|---|---|
| Operating the skill for a user (you ARE Claude Code running `/benchmark`) | [SKILL.md](SKILL.md). It is the canonical behavior spec: front-door flow, first-run wizard, dispatch table, voice rules, gotchas. Follow it exactly. |
| Explaining what this project is or installing it | [README.md](README.md) |
| Modifying the code, debugging a run, or reasoning about data files | [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) |
## The 60-second mental model
```
~/.claude/projects (user's real history, GBs of JSONL)
|
v extract_history.py (pure Python, local, no AI calls)
digest.json (a few hundred KB: unique prompts + corrections + metadata)
|
v build_eval_pack.py (LLM clusters into archetypes, freezes task cards)
…Read the whole file at its exact version.
How to install
mdr add earlyaidopters/gumroad-resources/resources/personal-ai-benchmark-kit/unpacked/personal_benchmark_skill/personal-benchmark/AGENTS.md@sha256:91c8f5edace0e4f1The line at the top of this page pins the label git:20260810.9572c5c, 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_qaso2dzruxr74wuw)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 10, 2026.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (6278 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
earlyaidopters/gumroad-resources · 48 stars · license none declared · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qaso2dzruxr74wuw GET https://markdownregistry.com/api/v1/resolve?ref=earlyaidopters/gumroad-resources/resources/personal-ai-benchmark-kit/unpacked/personal_benchmark_skill/personal-benchmark/AGENTS.md GET https://markdownregistry.com/api/v1/blob/91c8f5edace0e4f1e6f3d9acd212dd91187aa26188ed3d24043be87978f2cfb3
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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.