Git and workflow

15,303 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

change-summary

697

Muratify/agentspace

Skill Claude CodeCodex

Turn a git range into a change summary a human can read. Use for "what changed since last release", "write the release notes", "summarise this branch", or when a changelog entry is needed but the commit messages are noisy.

not rated 9 +1 2mo ago A 53 tokens

github-repo-audit

698

techysy/yangyu-hermes-skills

Skill Claude CodeCodex

A review process for checking whether a GitHub repository and its release materials are complete and consistent.

not rated 9 changed 19d ago A 133 tokens

synced-addons

699

kellerza/hass-addons

Cursor rule Cursor

Which add-on folders are CI-synced mirrors (do not hand-edit) vs maintained here.

not rated 9 6d ago A 616 tokens original Apache-2.0

theoklitosBam7/mcp-git-commit-generator

MCP server Claude CodeCodexCursor +2

One of 4 in mcp.json

MCP server "mcp-git-commit-generator" as configured in theoklitosBam7/mcp-git-commit-generator. Runs in Docker (ghcr.io/theoklitosbam7/mcp-git-commit-generator:latest).

not rated 9 4d ago A tokens not measured original MIT

PreToolUse

701

menot-you/n-memory

Hook Claude Code

One of 14 in hooks.json

Runs before the agent uses a tool for Bash, ExitPlanMode, Agent, Workflow, ^mcp__(plugin_nott_)?nmemory(-http)?__, Edit, Write, MultiEdit, Bash, Agent, Monitor, Workflow, AskUserQuestion, ExitPlanMode and mcp__.* tool calls, executing pynott-branch-lock.sh, bash-guards.sh, two-misses.sh, campaign-pr-guard.py…

not rated 9 changed 8d ago A tokens not measured AGPL-3.0

harlixay7/AgentXFlow

Skill Claude CodeCodex

Authoritative multi-agent engineering coordinator for parallel workflows with isolated Git worktrees, write scope locking, automated machine verification, and serialized FIFO merge queue.

not rated 8 changed 1mo ago A 35 tokens original MIT

osekkat/agent-skills

Skill Claude CodeCodex

Build and submit iOS apps to App Store Connect using fastlane (match/gym/pilot/deliver) or EAS (eas build / eas submit) for native (Swift/SwiftUI/UIKit), React Native, Expo, Flutter, and Capacitor projects. Use when archiving to .xcarchive, validating, uploading to TestFlight, configuring code signing and…

not rated 8 6mo ago A 142 tokens original MIT

quick-dev-setup

704

polygraphso/litmus

Skill Claude CodeCodex

Use when setting up a new Node.js project to install tooling and pre-commit hooks.

not rated 8 3mo ago A 23 tokens original Apache-2.0

auto-git-commit

705

ouyangyipeng/YatPotato

Cursor rule Cursor

A rule requiring an AI assistant to run Git operations after every code change, new file, or file deletion. Git is a tool for tracking changes to code and files.

not rated 8 1y ago A 0 tokens

from-issue

706

jeremymcs/skills

Skill Codex

Research and implement a code change from an existing issue, ticket, or issue-like artifact. Use when the user says "$from-issue", asks Codex to work from a GitHub issue, local markdown issue, tracker ticket, bug report, feature issue, or AFK implementation ticket, and expects codebase research, linked PR…

not rated 8 3mo ago A 92 tokens original MIT

commit

707

draeician/crules

Skill Claude CodeCodex

Version-guarded commit protocol — secret scan, SemVer triangulation, metadata sync, runtime validation.

not rated 8 3mo ago A 22 tokens

project-rules

708

peva3/anchor

Cursor rule Cursor

Cursor rule "project-rules" from peva3/anchor, covering cursor ai rules, core directives, critical enforcements, pre-commit checklist and required folders.

not rated 8 9d ago A 595 tokens original MIT

aegntic/aegntic-MCP

Command Claude Code

Command "jprompt_ultra_diff_review" from aegntic/aegntic-MCP, covering ultra diff review, task 1: create diff.txt, code review, diff and task 2: git diff and append.

not rated 8 1y ago A 0 tokens

issue-to-pr

711

DmitriyYukhanov/claude-plugins

Plugin Claude Code

Bundles 1 skill · 138 tokens together

Take a GitHub issue (bare, or tracked on a Project board) from triage to a merge-ready PR through a gated, worktree-isolated pipeline that scales its depth to the task and asks at most one batched question. The gates hold every run: design hardening, tests green, code review clean. Once you approve the PR in-session…

not rated 8 changed 19d ago A tokens not measured original MIT

gh-review-loop

712

OrenAshkenazy/gh-review-loop

Plugin Claude Code

Bundles 1 skill, 2 hooks · 71 tokens together

Clears AI reviewer feedback on your PR: reads real review-thread state, sweeps the sibling instances the reviewer missed, gates every push on your repo's own tests, then requests re-review — hard-capped at 3 re-review requests. Claude Code, Codex, Gemini and Copilot built in; any reviewer bot can be configured.

not rated 8 changed 8d ago A tokens not measured original MIT

tk

713

radutopala/ticket

Skill Claude CodeCodex

Git-backed ticket management for AI agents.

not rated 8 5mo ago A 9 tokens original MIT

implement

714

zhoushoujianwork/clawflow

Skill Claude CodeCodex

Implement an issue directly: analyze, test and repair, then create a branch and pull request.

not rated 8 +1 changed yesterday A 21 tokens

surface-after-care

715

ellmos-ai/skills

Skill Claude CodeCodex

Regelmäßiger Pflegedurchlauf für ein bereits veröffentlichtes GitHub-Repository (Stufe 1, günstig und oft wiederholbar): zuerst alle Distributionsflächen des Projekts ermitteln (npm, PyPI, Registries, Marketplaces, Stores, Website) und Änderungen später dorthin spiegeln, dann Topics setzen, Privacy-Gate, Dokumente auf…

not rated 8 2d ago A SkillSpector: warn 283 tokens original MIT

cadence

716

crenshawdev/cadence

Plugin Claude Code

Bundles 34 skills, 30 agents, 3 hooks · 2,294 tokens together

A plan/execute/verify loop for a single developer in Claude Code, with adversarial review at every gate: plans and diffs get refuted by a fresh Claude subagent or a panel of outside models (OpenAI, Gemini, DeepSeek), not just approved. State lives in files, not the conversation, so you clear aggressively and keep both.

not rated 8 changed today A tokens not measured original MIT

skillgate

717

renezander030/skillgate

Plugin Claude Code

Bundles 1 skill · 119 tokens together

Deterministic finish-line gates for AI coding agents — define done once in .skillgate/done.yaml, then block commit, push and publish until it passes. Wires a fail-closed PreToolUse hook, evaluates agent patches in a network-off clone, and keeps CLAUDE.md/AGENTS.md from drifting apart.

not rated 8 2d ago A tokens not measured original MIT

perforce

719

tjboudreaux/cc-plugin-perforce

Plugin Claude Code

Bundles 4 skills · 110 tokens together

4 Perforce version control skills for Claude Code covering basic operations, changelist management, conflict resolution, and shelving workflows.

not rated 7 +1 8mo ago A tokens not measured original MIT

github-pr-context-mcp

720

paarths-collab/github-pr-context-mcp

MCP server Claude CodeCodexCursor +2

Hardened Pure Context Retrieval Engine for GitHub PR History. Runs locally from the github-pr-context-mcp Python package.

not rated 7 9d ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: