agent-world-benchmark SKILL.md skillA
agent-world-benchmark from mangowhoiscloud/geode is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mangowhoiscloud/geode/agent-world-benchmark@git:20260825.9516eabPins git:20260825.9516eab in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mangowhoiscloud/geode
- Path
.agents/skills/agent-world-benchmark/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260825.9516eab, committed Aug 25, 2026
- Size
- 10,310 bytes
- Repository stars
- 15
- License
- Apache-2.0
Align, run, audit, and publish GEODE benchmark comparisons against Agent-World arXiv 2604.18292v1 across MCP-Mark, BFCL V4, and tau2-bench. Use for Agent-World or AgentWorld comparison requests, cross-suite agent benchmark design, Tau2 comparator/profile diagnosis, paired thin-runtime-versus-GEODE experiments, mean-accuracy@8 replication, or benchmark comparability and artifact reviews.
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
# Agent-World Benchmark Build evidence that separates an external paper reference from a causal GEODE runtime comparison. Never reconstruct missing Agent-World implementation details from its score table. First disambiguate the target. This skill covers Dong et al.'s Agent-World (`arXiv:2604.18292`), not Qwen's later `Qwen-AgentWorld-35B-A3B` and `AgentWorldBench` (`arXiv:2606.24597`). ## Security And Data-Handling Boundary This skill does not provide cryptographic services. It does not generate or manage keys, encrypt or decrypt data, create or verify signatures, or process certificates. The `task hash`, `prompt hash`, `policy hash`, and `schema hash` fields below are deterministic identities for non-secret canonical benchmark artifacts. They support reproducibility and change detection; they do not provide confidentiality, authentication, or authorization. Do not choose a cryptographic primitive or implement one inside a benchmark runbook. If a future benchmark genuinely requires encryption, signing, or certificate handling, stop and define a separately reviewed contract covering the security purpose, reviewed library or platform service, algorithm, key …
Read the whole file at its exact version.
How to install
mdr add mangowhoiscloud/geode/agent-world-benchmark@sha256:d4f955150204161eThe line at the top of this page pins the label git:20260825.9516eab, 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_vbqcdcjh4tqjyb74)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 25, 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 (10310 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
mangowhoiscloud/geode · 15 stars · license Apache-2.0 · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vbqcdcjh4tqjyb74 GET https://markdownregistry.com/api/v1/resolve?ref=mangowhoiscloud/geode/agent-world-benchmark GET https://markdownregistry.com/api/v1/blob/d4f955150204161ecc7880b94ba9efdddf3df853d74e06977c72dc77771c9d75
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.