skilld
All skills
av avatar

/workgraph

@d7c305c
by Ivan Charapanauav/skills16 stars
2

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 without caps. For clock-driven or metric-driven single loops, timeboxed-iterating and autoresearch remain lighter.

Ask your Agent

Use this Skill: https://skilld.dev/gh/av/skills/workgraph

This session only. Nothing lands on disk.

README.md

≈226 tokens on demand. Your agent reads this file only when SKILL.md points to it.

<img src="../assets/logos/workgraph.svg" width="72" align="left" hspace="12" alt="">

workgraph

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 without caps. For clock-driven or metric-driven single loops, timeboxed-iterating and autoresearch remain lighter.

npx skills add av/skills --skill workgraph

Part of av/skills — a library of agent skills for Claude Code, Codex, OpenCode and other coding agents.

Source: SKILL.md on GitHub

Third-party checks

No alerts1d3 checks · Risk SAFE
  • Gen Agent Trust Hub1d

    The skill orchestrates complex tasks by building and executing a directed graph of subagent actions. The main orchestrator agent relies on a 'Planner' subagent to analyze repositories and generate 'verification commands', which the orchestrator then executes to gate progress. This introduces a risk of indirect prompt injection, as malicious content within a target repository could influence the planner to generate harmful verification commands. Users should review the execution plan in Phase 1 before the loop begins.

  • Socket1d

    No alerts

  • Snyk1d

    Risk: LOW · No issues

Provenance

Signed by skilld at d7c305c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 2 weeks ago

README badge

README badge for av/skills/workgraph