arbor-executor SKILL.md skillA
arbor-executor from invergent-ai/surogates is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add invergent-ai/surogates/arbor-executor@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- invergent-ai/surogates
- Path
skills/research/arbor-executor/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Oct 27, 2026
- First version recorded
- Jun 13, 2026
- Size
- 3,995 bytes
- Repository stars
- 28
- License
- AGPL-3.0
The Arbor executor workflow: clone the repo from the git bundle your brief hands you, implement and evaluate exactly ONE hypothesis with the file tools, then report structured results via worker_complete. Preloaded automatically on arbor-executor task workers. Never touch the held-out test split.
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
# Arbor Executor — Experiment Workflow You are an executor for an autonomous research run. Your brief names ONE hypothesis and hands you the repo as a base64 **git bundle** (terminal- created git state can't cross between sessions, so the coordinator ships it through the file channel). Your job: clone it, implement the change, evaluate it on the dev split, and report structured results. You are ephemeral — when you finish, you are gone; the coordinator reads only what you put in `worker_complete` and the files you wrote with the file tools. ## The 7 steps 1. **SET UP** — run the bundle/clone commands from your brief EXACTLY: decode `repo.bundle.b64`, `git clone` it into your work dir, `cd` there. Then read the hypothesis and ancestor insights. 2. **BASELINE** — sanity-check that the dev eval command runs on the freshly-cloned repo before you change anything. 3. **PLAN** — the smallest change that tests the hypothesis. Nothing more. 4. **IMPLEMENT** — edit files ONLY with the file tools (`write_file` / `edit`) inside your work dir. A shell redirect (`>`, `sed -i`, `tee`, `cat <<EOF`) will NOT survive out of your sandbox — your change reaches …
Read the whole file at its exact version.
How to install
mdr add invergent-ai/surogates/arbor-executor@sha256:ed8162c5affa031aThe line at the top of this page pins the label v1.0.0, 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_wqun2eazyma65wyd)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 13, 2026 and Oct 27, 2026, about one every 34 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-10-27 | 7da1fa4 | 3,995 B | A | view · diff |
| v1.0.0 | 2026-10-12 | f6e8148 | 3,849 B | A | view · diff |
| v1.0.0 | 2026-06-14 | 91275b1 | 3,813 B | A | view · diff |
| v1.0.0 | 2026-06-13 | 582c8a0 | 3,316 B | A | view · diff |
| v1.0.0 | 2026-06-13 | fbfd776 | 2,957 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 (3995 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
invergent-ai/surogates · 28 stars · license AGPL-3.0 · pushed 2026-11-05 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_wqun2eazyma65wyd GET https://markdownregistry.com/api/v1/resolve?ref=invergent-ai/surogates/arbor-executor GET https://markdownregistry.com/api/v1/blob/ed8162c5affa031ae9f72d8d55c019d322c7231899a40d55f9bdad5585cb4c1a
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.