workflow SKILL.md skillA
workflow from mweinbach/agent-coworker is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mweinbach/agent-coworker/workflow@git:20260905.cfba839Pins git:20260905.cfba839 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mweinbach/agent-coworker
- Path
skills/workflow/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260905.cfba839, committed Sep 5, 2026
- First version recorded
- Jul 26, 2026
- Size
- 10,409 bytes
- Repository stars
- 156
- License
- a license file GitHub does not identify
Author and run a deterministic multi-agent workflow — a JavaScript script that fans out, pipelines, loops, and judges across many child agents. Use when the work decomposes into many similar units (review every changed file, research N topics, migrate M call sites), when it needs adversarial verification or a judge panel, or when the user asks to "use a workflow", "fan out agents", or be exhaustive. Do not use for a single delegated task — spawnAgent is cheaper.
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
# Workflows A workflow is a script you write that orchestrates child agents in real code. The harness runs it in a sandbox and drives `AgentControl` from it. The patterns below are available orchestration techniques, not mandatory review rounds. Respect the user's requested scope and task-specific review limits. Use additional discovery rounds for explicitly exhaustive work or when new evidence warrants them; ordinary PR feedback handling does not require discovery until dry. Explicit user instructions override this skill's defaults within higher-priority instructions and enforced tool boundaries. Infer routine reversible details and finish the authorized workflow. If a requirement genuinely blocks progress, name this `SKILL.md`, quote the instruction, and explain the concrete decision needed. Keep handoffs and final results concise and readable. ## When this is worth it Reach for a workflow when the work is **wide** (many similar units) or needs **structure** (verify each finding independently, judge N candidates, loop until nothing new turns up). One `workflow` call replaces dozens of `spawnAgent` / `waitForAgent` calls and keeps their transcripts out of your context. …
Read the whole file at its exact version.
How to install
mdr add mweinbach/agent-coworker/workflow@sha256:e3ad81c30d49b8e2The line at the top of this page pins the label git:20260905.cfba839, 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_h2p4ie244bzign7t)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 26, 2026 and Sep 5, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260905.cfba839 latest | 2026-09-05 | cfba839 | 10,409 B | A | view · diff |
| git:20260904.d2e3de3 | 2026-09-04 | d2e3de3 | 9,356 B | A | view · diff |
| git:20260826.e0e682e | 2026-08-26 | e0e682e | 9,032 B | A | view · diff |
| git:20260803.983e430 | 2026-08-03 | 983e430 | 8,629 B | A | view · diff |
| git:20260726.e581f9c | 2026-07-26 | e581f9c | 7,128 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 (10409 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
mweinbach/agent-coworker · 156 stars · license a license file GitHub does not identify · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_h2p4ie244bzign7t GET https://markdownregistry.com/api/v1/resolve?ref=mweinbach/agent-coworker/workflow GET https://markdownregistry.com/api/v1/blob/e3ad81c30d49b8e2b3254f02be03c5acea5eace03a5ce94662e74f2968e5a8d4
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 mweinbach/agent-coworker
Every file in mweinbach/agent-coworker