workgraph SKILL.md skillA
workgraph from av/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add av/skills/workgraph@git:20261020.f0b3811Pins git:20261020.f0b3811 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- av/skills
- Path
workgraph/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261020.f0b3811, committed Oct 20, 2026
- First version recorded
- Aug 3, 2026
- Size
- 22,865 bytes
- Repository stars
- 28
- License
- MIT
Orchestrate work as a cyclic directed graph of subagent-executed nodes with transition criteria on edges, budgeted cycles, and per-node gates (runtime verification, metric, or artifact). Use when the user says "workgraph", "run this as a graph", "graph this work", or when a goal has parallel branches, feedback loops, or mixed gate types that a linear loop cannot express. Every node is sized to a 64k context budget, so small goals run as a two-node do/verify graph and large goals scale out…
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
# Workgraph
Work expressed as a directed graph. Nodes are units of work executed by
subagents. Edges carry transition criteria. Cycles are allowed — and budgeted.
You are the **orchestrator**: router, scheduler, gatekeeper, scribe. All
productive work happens inside subagents. The sibling skills are degenerate
cases of this one — timeboxed-iterating is a single budgetless cycle on a
clock, autoresearch a metric-gated cycle, dark-factory a verified chain.
The one sizing rule: **every node fits a 64k context budget**. The planner
estimates each node from the task and sizes it to that budget. A goal that
fits one node is a two-node graph (`do → verify`) and runs with no further
ceremony; a very large goal is a large graph. Nodes are sized to the
budget, never to a target count.
```
Plan ──► lint ──► ┌─► route ─► schedule ─► dispatch ─► gate ─► log ─┐
│ │
└────────────── graph still live ─────────────────┘
└── exit signal ──► final summary
```
## Role and Iron Laws
```
1. YOU DO NO WORK. You route, schedule, dispatch, gate, and log. Exploring
…Read the whole file at its exact version.
How to install
mdr add av/skills/workgraph@sha256:32ca806ffd1dbc37The line at the top of this page pins the label git:20261020.f0b3811, 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_wwzgw4nhkvrbz5dr)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 3, 2026 and Oct 20, 2026, about one every 26 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261020.f0b3811 latest | 2026-10-20 | f0b3811 | 22,865 B | A | view · diff |
| git:20260920.d7c305c | 2026-09-20 | d7c305c | 22,698 B | A | view · diff |
| git:20260803.7f28ae6 | 2026-08-03 | 7f28ae6 | 15,404 B | A | view · diff |
| git:20260803.1818a8e | 2026-08-03 | 1818a8e | 13,130 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 (22865 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
av/skills · 28 stars · license MIT · pushed 2026-10-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_wwzgw4nhkvrbz5dr GET https://markdownregistry.com/api/v1/resolve?ref=av/skills/workgraph GET https://markdownregistry.com/api/v1/blob/32ca806ffd1dbc373b117db951530266f3a8a2401432a439bc773c388e080ace
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.