benchmark SKILL.md skillA
benchmark from eltmon/overdeck is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add eltmon/overdeck/benchmark@git:20261001.c98f934Pins git:20261001.c98f934 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- eltmon/overdeck
- Path
sync-sources/skills/benchmark/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261001.c98f934, committed Oct 1, 2026
- First version recorded
- May 22, 2026
- Size
- 3,153 bytes
- Repository stars
- 34
- License
- MIT
Create a benchmark issue to test Overdeck's agent pipeline. Creates a GitHub issue from a stored template with a scenario label for A/B comparison of models and approaches.
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: QuantumLlama Provider Integration ## Overview Creates a GitHub issue from the QuantumLlama benchmark template, appended with a scenario description for A/B testing. The normal Overdeck pipeline (workspace creation, agent work, review, test) then exercises the full system. Results (cost, tokens, quality) are tracked per-workspace for comparison across runs. ## When to Use - User wants to benchmark Overdeck's agent pipeline - User wants to compare model performance (e.g., Opus vs Sonnet vs OpenAI) - User wants to measure token consumption and cost for a feature implementation - User says `/benchmark <scenario description>` ## Usage ``` /benchmark <scenario description> ``` **Examples:** - `/benchmark Opus 4.6 baseline` - `/benchmark All OpenAI models` - `/benchmark Sonnet 4.6 with RTK enabled` - `/benchmark Haiku fast mode, no planning` ## What This Does 1. Reads the issue template from `benchmarks/templates/quantumllama.md` 2. Creates a GitHub issue titled: `Benchmark: QuantumLlama — <scenario description>` 3. Labels it with `benchmark` (creates the label if it doesn't exist) 4. Reports the issue number so the user can proceed with `pan start PAN-XXX` …
Read the whole file at its exact version.
How to install
mdr add eltmon/overdeck/benchmark@sha256:6132fd167e29f8e0The line at the top of this page pins the label git:20261001.c98f934, 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_5v5bbzsrf62oejaj)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between May 22, 2026 and Oct 1, 2026, about one every 26 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261001.c98f934 latest | 2026-10-01 | c98f934 | 3,153 B | A | view · diff |
| git:20260924.f5d6c8e | 2026-09-24 | f5d6c8e | 3,154 B | A | view · diff |
| git:20260618.ccb1e75 | 2026-06-18 | ccb1e75 | 3,153 B | A | view · diff |
| git:20260618.80fba74 | 2026-06-18 | 80fba74 | 3,177 B | A | view · diff |
| git:20260523.08fffdd | 2026-05-23 | 08fffdd | 3,185 B | A | view · diff |
| git:20260522.817c2c7 | 2026-05-22 | 817c2c7 | 3,218 B | A | view |
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 (3153 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
eltmon/overdeck · 34 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5v5bbzsrf62oejaj GET https://markdownregistry.com/api/v1/resolve?ref=eltmon/overdeck/benchmark GET https://markdownregistry.com/api/v1/blob/6132fd167e29f8e00fdd77979004c991d3e60c8141ca7e83cac512d4b4ebf494
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.