loop-graph
Author and optionally direct-launch one durable loop-graph run as executor, ledger, directives, and supervisor artifacts under a dated `.longgraph` directory, then present copy-ready host prompts. Use for multi-round work with gated milestones, independent audit, cross-host execution, or durable state. Detect Codex or Claude Code from context and create both same-host runtime nodes when the owner chooses direct launch. Existing runtime nodes are self-contained.
Profile →npx skills add levi-qiao/graphkit --skill loop-graph --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# loop-graph — a graph of agent nodes, not a drifting loop ## What it does & why Turns a vague long-horizon request ("make it production-ready", "accuracy above baseline", "finish the migration") into a small **graph of agent nodes** that stays on-spec across many rounds: - an **executor node** — drives the work round by round against a single scoreboard; - a **supervisor node** — audits the work from *outside* the executor's context (re-verifying claimed-done against the shared standards) and corrects course before drift compounds. Why a graph, not a loop: an agent grinding a long task **is inside the context that drifted**, so it rationalizes scope creep and calls half-done work "done". The nodes talk only through durable, inspectable state (ledger, git tree, directives file) — never a shared, polluted context. **Each node runs on its own timer, and no node ever wakes another.** The executor fires, closes several verified rounds on warm context, and ends. The supervisor fires on a slower cadence, audits, appends corrections, and ends. A correction is picked up on the executor's next fire. Two independent clocks and one file edge — no dispatch, no resume prompt, no liveness protoc
- What it does & why
- The graph it builds
- When to use it
- Language
- How to run it
- The rules that make it work (encoded in the templates)
- Files in this skill
What does the loop-graph skill do?
Author and optionally direct-launch one durable loop-graph run as executor, ledger, directives, and supervisor artifacts under a dated `.longgraph` directory, then present copy-ready host prompts. Use for multi-round work with gated milestones, independent audit, cross-host execution, or durable state. Detect Codex or Claude Code from context and create both same-host runtime nodes when the owner chooses direct launch. Existing runtime nodes are self-contained.
How do I install it?
Run `npx skills add levi-qiao/graphkit --skill loop-graph --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From levi-qiao/graphkit, a repository with 23 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.