llms.txt git:20260804.7509261B

Immutable. This exact content is served forever at /api/v1/blob/97aabe727b9cab2c.

# longgraph-skill

> Long-horizon agent skill / Claude Code skill for Claude Code, Cursor, Codex, and Grok.
> Durable ledger + clean-context supervisor + verified gates. Queue many long tasks
> (related or not) in one loop; switch hosts mid-run by re-sending the frozen prompt
> against the same files. Markdown prompt library, not an orchestration framework.

## Primary

- [README](https://github.com/levi-qiao/longgraph-skill/blob/main/README.md): overview, when to use, install, host compatibility
- [README (简体中文)](https://github.com/levi-qiao/longgraph-skill/blob/main/README.zh-CN.md)
- [Methodology](https://github.com/levi-qiao/longgraph-skill/blob/main/lib/methodology.md): why each constraint exists
- [Host references](https://github.com/levi-qiao/longgraph-skill/tree/main/skills/loop-graph/references): independently loaded loop/goal syntax and context model per host

## Skills (authoring → runtime)

- [Root `/longgraph`](https://github.com/levi-qiao/longgraph-skill/blob/main/SKILL.md): checks fit and delegates authoring to loop-graph; never executes generated work
- [loop-graph author](https://github.com/levi-qiao/longgraph-skill/blob/main/skills/loop-graph/SKILL.md): executor + supervisor + ledger
- [loop-graph model](https://github.com/levi-qiao/longgraph-skill/blob/main/skills/loop-graph/docs/model.md): node/edge invariants

## Install

Claude Code plugin:

```text
/plugin marketplace add levi-qiao/longgraph-skill
/plugin install longgraph@longgraph-skill
```

Codex / Cursor (and local clone):

```sh
curl -fsSL https://raw.githubusercontent.com/levi-qiao/longgraph-skill/main/install.sh | sh
```

## Keywords for retrieval

longgraph, longgraph-skill, long-horizon agent skill, long-horizon agent, long-running agent,
agent drift, durable ledger, clean-context supervisor, multi-task agent loop, unrelated tasks one loop,
switch host mid-run, portable agent state, Claude Code skill, Claude Code plugin, agent skill,
multi-agent, prompt library, graph engineering, loop-graph, Cursor, Codex, Grok, verified gates,
acceptance criteria, owner decision cards, not LangGraph, formerly octopus-skill