mcpField

longgraph

github.com/levi-qiaoAgent workflows157 installs
Repository

About longgraph

longgraph is a set of skill entry points for routing durable work through a shared compiler and executor. Focused entries cover code consolidation, incremental delivery, and research; self-contained tasks are directed to the host directly.

Key features

  1. 01Share the loop-graph compiler
  2. 02Route work to focused skill entries
  3. 03Support durable state and gates
  4. 04Define ownership boundaries and independent verification

Use cases

  1. 01Consolidate duplicated or unused code over multiple rounds
  2. 02Implement requirements incrementally with acceptance evidence
  3. 03Compare approaches using open-source implementations and experiments
  4. 04Orchestrate work that needs durable state

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/levi-qiao/longgraph-skill --skill longgraph

After installing, type/longgraphin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

.gitignore
CLAUDE.md
AGENTS.md
CONTRIBUTING.md
install.sh
README.zh-CN.md
LICENSE
llms.txt
README.md
.claude-plugin/
marketplace.json
plugin.json
.github/
PULL_REQUEST_TEMPLATE.md
.github/ISSUE_TEMPLATE/
feature_request.md
bug_report.md
.github/workflows/
grok-bot-pr-relay.yml
grok-bot-issue-relay.yml
docs/
public-private-boundary.md
lib/
methodology.md
skills/loop-converge/
README.zh-CN.md
README.md
preset.md
skills/loop-deliver/
README.md
README.zh-CN.md
preset.md
skills/loop-graph/
README.zh-CN.md
README.md
skills/loop-graph/docs/
model.md
preset-contract.md
skills/loop-graph/examples/migrate-blob-storage/
README.md
skills/loop-graph/examples/migrate-blob-storage/archive/
rounds.md

Details

From the project README

longgraph — route to the right durable run

longgraph has one shared compiler, loop-graph, and focused entries that bind only goal-specific rules. All compile the same executor, supervisor, ledger, directives, and ops artifacts. Do not execute the generated runtime nodes from this authoring skill.

Fit and route

  • Use loop-converge for multi-round unused code, duplication, consolidation, reuse, or slimming.
  • Use loop-deliver for a product or engineering requirement that needs incremental implementation and acceptance proof.
  • Use loop-research to compare feasible approaches with open-source implementations, primary research, and controlled experiments before committing to one.
  • Use loop-graph directly only when none of the focused packs fits but the work still needs durable state, gates, owner boundaries, host switching, or independent verification.
  • If the request is one self-contained task that fits a normal host goal/task, explain that longgraph adds no value and recommend sending the task directly. Do not wrap it in another objective or invent a lighter longgraph mode.

Shared reference: lib/methodology.md explains why the graph's discipline exists. The baseline and pack boundary is in skills/loop-graph/docs/preset-contract.md.

Comments

Markdown supported