dag plugins

8 tagged dag, measured the same way as everything else here.

lean4

01

frenzymath/Archon

Plugin Claude Code

Bundles 1 skill, 11 commands, 4 agents, 3 hooks · 404 tokens together

Archon's modified Lean 4 plugin (draft, formalize, autoformalize, prove, autoprove, checkpoint, review, refactor, golf, learn, doctor) — forked from cameronfreer/lean4-skills.

not rated 225 +1 2mo ago A tokens not measured original Apache-2.0

taskflow

02

heggria/taskflow

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 122 tokens together

Declarative, verifiable DAG orchestration for Claude Code subagents — fan-out, gates, loops, tournaments, approvals, resumable runs, and saveable commands, with intermediate transcripts kept out of your context.

not rated 78 +2 changed 7d ago A tokens not measured original MIT

lossless-code

03

GodsBoy/lossless-code

Plugin Claude Code

Bundles 1 skill, 7 hooks, 1 MCP server · 23 tokens together

DAG-based lossless context management for Claude Code. Every message from every session is persisted in a SQLite vault with FTS5 search. Summaries form a directed acyclic graph - nothing is ever lost.

not rated 15 5mo ago A tokens not measured original MIT

forkmind

06

Medhovarsh/forkmind

Plugin Claude Code

Bundles 2 skills, 1 command, 2 agents, 1 MCP server · 487 tokens together

Local-first LLM branching, debugging & context offloading. Treat AI context windows like a Git repo — capture, branch, regression-test LLM calls as a DAG, and archive context as encrypted, restorable capsules. Teaches Claude when and how to drive ForkMind.

not rated 3 1mo ago A tokens not measured original MIT

check-my-skills

07

tonyfadel23/skill-inspector

Plugin Claude Code

Bundles 3 skills · 256 tokens together

Parse, visualize, and audit SKILL.md files as interactive DAGs with quality scoring and structural diagnostics.

not rated 2 6mo ago A tokens not measured original MIT

graph-engineering

08

sciencemj/graph-engineering

Plugin Claude Code

Bundles 1 skill, 5 commands, 1 hook, 1 MCP server · 141 tokens together

Runs coding work as an explicit execution graph (DAG) instead of a natural-language conversation. Deterministic work is executed by the server with zero LLM calls, the points where a human steps in are declared in the graph, and run state is owned by the server rather than the conversation.

not rated 0 2mo ago A tokens not measured original MIT