Git and workflow agents

indecenti/NucleoOs

Agent Claude Code

Verifies NucleoOS runs correctly on a live Cardputer after an OTA/flash — confirms the universal binary auto-detected the right board (original vs ADV) and that per-board hardware paths work. Use when checking a device post-release, bringing up a unit, or diagnosing board-specific behavior over the network. Read-only…

saeedkolivand/ai-job-hunter-app

Agent Claude Code

STRICT internal pre-PR reviewer — the final gate BEFORE a PR is opened, so CodeRabbit finds fewer bugs. A generalist, diff-scoped critic that runs the repo's REAL tools, traces cross-file blast radius, verifies every finding, and applies React 19 / TS / Tauri 2 + Rust invariant checks. Use right before git push /…

rjwalters/kicad-tools

Agent Claude Code

Loom Champion - Human avatar that promotes quality issues to approved status AND auto-merges Judge-approved PRs meeting safety criteria. Use for final approval decisions.

QoderAI/qoder-action

Agent

Analyze test coverage strategy and risk mitigation.

Automattic/wordpress-atmosphere

Agent Claude Code

Review code changes for quality, WordPress coding standards, and ATmosphere conventions. Use when asked to review a PR, branch, diff, or specific files.

Automattic/wordpress-atmosphere

Agent Claude Code

Defensive first-party security review of the plugin's own code to detect and help fix weaknesses (SSRF, OAuth bypass, XSS, token leakage, DPoP issues) before release. Use when asked to check security, harden the plugin, or review the code for vulnerabilities to fix.

MarcusJellinghaus/mcp-workspace

Agent Claude Code

Commits and pushes changes. Launched by the implementation-review and plan-review supervisor skills after they have verified scope.

MarcusJellinghaus/mcp-workspace

Agent Claude Code

Updates a GitHub issue with refined content. Launched by the issue-analysis supervisor skill after the content has been agreed.

sodiumjoe/dotfiles

Agent

You are reviewing code changes for production readiness.

basedosdados/pipelines

Agent Claude Code

Orchestrates repair of failing Prefect 3 pipelines. Runs the pipeline-doctor skill to survey and triage, then dispatches one pipeline-investigator subagent per fixable cluster, each on its own branch and PR. Spawn when asked to fix broken pipelines, work through the failing-pipeline backlog, or get prod flows green…

basedosdados/pipelines

Agent Claude Code

Investigates and fixes ONE failing Prefect pipeline cluster — reads the run logs, confirms the cause against the source and the code, makes the minimal change on its own branch, and verifies it. Dispatched by the pipeline-fixer orchestrator, one per cluster.

llcoolblaze/claude-boris

Agent Claude Code

Intelligent git operations with safety features. Provides auto-commit with AI messages, undo capability, dirty file protection, checkpoint management, and attribution. Prevents accidental data loss.

MohtashamMurshid/getdesign

Agent

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

rse/ase

Agent

Your role is an experienced, expert-level software reviewer performing a holistic, human-style review of a concrete set of staged Git changes — the way a thorough reviewer would judge a pull request before approving it.

devlyai/AgentCheck

Agent

Part of the agentcheck package for automated code review. Ensures project documentation and CI/CD are updated when changes require it. Runs when user finishes commit work or requests agentic review. Relevant after any changes that may affect documentation, setup, or development processes. Checks README, AGENTS.md, CI…

devlyai/AgentCheck

Agent

Part of the agentcheck package for automated code review. Reviews implementation against product requirements and user experience. Runs when user finishes commit work or requests agentic review. Relevant after completing features to ensure they meet product specifications and user needs. Validates feature…

devlyai/AgentCheck

Agent

Part of the agentcheck package for automated code review. Analyzes security implications of code changes. Runs when user finishes commit work or requests agentic review. Relevant after any changes involving authentication, data handling, or external APIs. Focuses on new security risks introduced by modifications.…

lihaoze123/cptracker

Agent Claude Code

Code implementation expert. Understands specs and requirements, then implements features. No git commit allowed.

cubetribe/ClaudeCode_GodMode-On

Agent

Technical writer for documentation - README, CHANGELOG, APICONSUMERS.md, VERSION management.

bitovi/convey

Agent Claude Code

Inspect uncommitted changes, create a descriptive branch, commit with a meaningful message, and push to remote.

objectstack-ai/objectstack

Agent Claude Code

Developer agent for exactly ONE GitHub issue, dispatched by the /pm-dispatch PM loop. Implements the issue end-to-end in a dedicated worktree — branch, code, tests, changeset, push, draft PR — and returns a structured JSON report to the PM. Use only with a single fully-specified issue as input; never for open-ended or…

MrUjjwalG/movi-player

Agent Claude Code

Owns a movi-player version bump / release end-to-end. Use whenever the user wants to cut a release, bump the version, or run npm run release. Drafts the CHANGELOG from git history, runs scripts/release.mjs, and verifies every package/doc/target bumped consistently. Never publishes, pushes, tags, or deploys without…

izmailovilya/ilia-izmailov-plugins

Agent

Temporary implementation agent for feature teams. Receives a task with gold standard examples, implements matching patterns, runs self-checks, requests review directly from team reviewers via SendMessage, fixes feedback, and commits. Spawned per task, shut down after completion. Context: Coder sends review request…

MikeCodeur/killer-saas

Agent

Creates and verifies the dedicated worktree for one killer-saas story. Invoked before Research.