Agent Workflows · Git

Takes a task through to a merged pull request in an isolated git worktree, splitting it into small independent PRs and looping on CI and review gates until they pass.

code-yeongyu/oh-my-openagent

Audit, score, and compare repositories containing portable Agent Plugins against the official Agent Plugins specification.

fabricioctelles/skills

Runs a read-only assessment in one of two modes, a repository health check or a runtime extension gap review, and reports findings as a markdown table.

openJiuwen-ai/agent-core

Turns a one-line objective into a multi-step plan file with PR-sized steps, context briefs, a dependency graph, parallel-step detection and an adversarial review.

affaan-m/ECC

Configure and optimize Starship cross-shell prompt with presets, custom modules, and performance tuning.

wcygan/dotfiles

Facilitates a read-only standup between git worktrees, branches or PRs, where each acts as an agent in a shared markdown chat to agree one consolidation plan.

thedotmack/claude-mem

Write or resume a handoff document so the next agent session can pick up the current work.

haacked/dotfiles

Coordinate with other agents/humans via the optional Interlinked MCP Server, and use local checkpoints & file reservations.

QuentinCody/interlinked-cli

The single entry point for the AgentSystem engineering pipeline.

AgentSystemLabs/core

Audits git worktrees and removes the ones that are safe to delete — merged into the base branch (including squash-merges via gh), missing on disk, or explicitly confirmed by the user — then deletes…

novuhq/novu

Runtime-V2 kernel-writing workflow. An agent skill from mirage-project/mirage.

mirage-project/mirage

Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact…

pedrohcgs/claude-code-my-workflow

Interactively "taste the CLI" and "kick the tires" on any CLI tool or subcommand (/manual-cli-test, /agent-cli-kick-tires).

pigweed-project/pigweed

Guides use of Worktrunk (wt), a CLI that makes git worktrees as easy as branches so several AI agents can work in parallel on isolated branches.

jjmartres/opencode

mini-harness · initialize or re-initialize a repo's memory under .harness/repoinfo/ with a multi-agent pass — three-perspective codebase overview, ranked scripts map, issue scan, git-seeded update…

HangYu8123/mini-harness

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments.

trpc-group/trpc-agent-go

Cut or check Runner nightlies — one workflow for macOS and Windows, one public prerelease, shared stamp, and separate stable feeds

yicheng47/runner

只讀審閱 Pi 藍皮書畢業專案的需求覆蓋、修改範圍、導航連接和驗收證據；用於實現完成後的獨立複核. An agent skill from xiaomoBoy/pi-bluebook.

xiaomoBoy/pi-bluebook

Updates the enhanced Telegram plugin for Claude Code from its GitHub repository: compares file hashes, shows recent commits, asks first, then runs the installer.

k1p1l0/claude-telegram-supercharged

세션 종료 시 Memory, Handoff를 자동 정리. /pack

ten-builder/ten-builder

Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures.

Dimillian/Skills

Audit and update CLAUDE.md files (root or any directory-scoped one) against the actual current state of the code they document.

therxmv/Telegram-Themer

Unattended-run kernel for Grok Bot non-git work. An agent skill from aigorahub/elves.

aigorahub/elves

A skill your agent uses when the strategist drafts per-issue graded checks after decomposition and before builder dispatch.

DanMcInerney/architect-loop

Use Cortex decision memory through the normal Memtrace MCP tools.

syncable-dev/memtrace-public

Resolve canonical Git checkouts, index and verify codebase-memory-mcp graphs through the guarded CLI, open its browser viewer on request, and safely audit duplicate worktree caches.

vincentkoc/dotskills

Project Manager skill. An agent skill from Apra-Labs/apra-fleet.

Apra-Labs/apra-fleet

Measure a branch against the commit it stands on — extract the base instead of flipping the working tree, pick the base by hash, and prove a new test case red on it.

stylelint-stylistic/stylelint-stylistic

M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。

Towow-ai/Flowness

Answers structural questions about a repository, such as where a symbol is defined, what calls it and what changed recently, through the basemind MCP server.

Goldziher/basemind

Comprehensive onboarding for new or returning contributors. An agent skill from DeL-TaiseiOzaki/claude-code-orchestra.

DeL-TaiseiOzaki/claude-code-orchestra

Review uncommitted code changes using parallel Claude sub-agents (Bug Hunter, Rules Auditor, optional Architect).

peterkrueck/Claude-Code-Development-Kit

Starts a feature as a demo narration instead of a PRD: you approve the script before any code, then the agent builds in a fresh worktree and opens a PR with proof.

Devin-AXIS/iPolloWork

A skill your agent uses when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees in .worktrees/

aaddrick/claude-pipeline

Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically.

guaardvark/guaardvark

Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation.

poshan0126/dotclaude

Initialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git

Stanshy/AgentHub

审查并在独立授权后合并一个 GitHub PR。用于单 PR 的 current-head SubAgent Review、按证据调用专项 Review、落地与 parity readback；裸分支或缺失 PR 转交 git-push-pr。

Dimon94/skills

Creates isolated git worktrees, with optional tmux sessions, for PR reviews, issue fixes and feature work across projects and repositories.

Yeachan-Heo/oh-my-claudecode

How to manually e2e-test each EDT-MCP server tool against a live EDT workbench + TestConfiguration.

DitriXNew/EDT-MCP

Pre-submit 自检——envelope 提交 commit gate 前必跑。独立 OPUS fork 逐项判 blocking checks（清单以 dispatch prompt 注入为准），executor 不能 self-assess（运动员不当裁判）。

Towow-ai/Flowness

A skill your agent uses when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell.

Sma1lboy/rove

Builds a two-phase implementation plan from a spec issue, analysis or concept, writing a detailed test plan first and the implementation outline second.

gittower/git-flow-next

Drives the basemind code-intelligence tool from the command line for symbol search, callers, git history and blame, document search and web crawling, sharing its cache with the MCP server.

Goldziher/basemind

Audits a repository's file layout and project documentation against a written convention file, then proposes moves, deletions and doc fixes as an approved plan before touching anything.

TyrealQ/q-skills

Sets up an autonomous research loop where an agent runs experiments on git branches, logs results and proposes the next iteration while you approve each hypothesis change.

LearnPrompt/andrej-karpathy-skills

Update project documentation after code changes. An agent skill from peterkrueck/Claude-Code-Development-Kit.

peterkrueck/Claude-Code-Development-Kit

Makes a repository Superset-ready by writing .superset/config.json with setup, teardown and run scripts, then proving it with a real throwaway workspace.

superset-sh/superset