crussella0129

Animus Sprint Loops — Development skill for Claude Code

Development community

A lightweight, platform agnostic protocol for autonomous development and objective handling (repo acts as a Claude Code Plugin Marketplace, Codex Skill, Antigravity Skill, as well as a drop-in skill f.

How to install Animus Sprint Loops

This entry records only its repository, not the path inside it, so there is no exact command to give. Open crussella0129/Animus_Sprint_Loops and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Animus Sprint Loops does

Alternatives in Development

Claude SEO — Multi-Platform Agent Instructions — For Cursor, Cursor Cloud Agents, Google Antigravity, and Gemini CLI 5k ★
Om Tidy — Self-maintenance pass — acts on every hygiene flag: archives completed work, groups loose clusters, splits ove 4.6k ★
Desloppify — Agent harness to make your slop code well-engineered and beautiful 3k ★

README

Animus Sprint Loops

Animus Sprint Loops turns a project's documentation into a living **Project Book**: one durable, linkable record of intended outcomes, active work, realization evidence, and the sprint history that connects them. Work advances through **Research → Plan → Build → Test → Loop**, with state derived from Book evidence on disk.

Quick start

Sprint Loops runs the same five-phase workflow through whichever runtime you already use. The fastest path:

**1 — Install an adapter.** Pick your runtime from [Choose an adapter](#choose-an-adapter) and follow its guide. For Claude Code, add the marketplace and install the plugin from an interactive session:

/plugin marketplace add crussella0129/Animus_Sprint_Loops
/plugin install sprint-loop@sprint-loops

**2 — Start or resume a loop.** From your project root, invoke the adapter (Claude Code shown; see the table for Codex, Antigravity, and open harnesses):

/sprint-loop:sprint-loop start ""

Invoke it with no argument (or `continue`) to resume whatever phase the Book reports.

**3 — What happens.** Every run begins at the **substrate gate** (`check-substrate.sh`):

On a brand-new project it reports substrate-absent and runs convergence (deploy-substrate.sh), which creates the docs/ Book, the main / dev branches, the work ledgers, a remote profile (`schemas/remote-profile.md`), the first sprint, and the substrate contract stamp.
On a project set up by an older bundle it reports substrate-outdated:-> and runs the same command. Spin-up and upgrade are one idempotent operation — see Convergence: spin-up and upgrade are one command.
On an established, current project it reports substrate-complete and hands off to routing, which advances the sprint through Research → Plan → Build → Test → Loop. Each phase writes its