4,322 tagged Git and workflow, measured the same way as everything else here.
Browse within: agent-orchestration 69Multi-Agent 52agentic-workflow 50agentic 40agentic-coding 39Autonomous Agents 36code-quality 35claude-plugin 32ai-assisted-development 30spec-driven-development 29rust 28typescript 28bun 27claude-ai 26
Agent
Use this agent when you need to research a library, repository, or code pattern without polluting the main conversation context. Spawns an isolated lookup using DeepWiki, Context7, Exa, git clone, and Web Search+Fetch, then returns concise findings. Accepts arbitrary natural-language queries, repo slugs, library…
Agent
Thin wrapper around git-agent CLI. Routes the user's intent to the right git-agent CLI subcommand. By default, any input is treated as a commit intent and passed to git-agent commit --intent. Runs when the user @git-agent, asks to "check git health", "review repo setup", "scan for secrets", "update gitignore"…
Agent
Use this agent before shipping, merging, or deploying changes. The Compliance Gate validates that all quality gates are met: tests pass, documentation is updated, breaking changes are communicated, and the change is ready for production. Context: User wants to merge a feature branch user: "I think this PR is ready to…
Agent
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Agent Claude Code
Reviewer-class. Read-only review of what other departments commit to — contract terms, privacy and data handling, risk acceptance, and compliance findings. Holds no write surface. Its findings are not overrulable by the department under review.
Agent Claude Code
Reviewer-class. Read-only security review of what other departments build — authorization, data handling, secrets, dependencies, and designs that create exposure. Holds no write surface. Blocking findings are not overrulable by the department under review.
Agent
Drafts CHANGELOG entries from git log applying pm-skills CHANGELOG hygiene rules from CLAUDE.md: describe what changed (not where), public paths only, never reference gitignored NOTES/ or agent-context/SESSION-LOG/ or docs/internal/efforts/. Distinguishes user-facing from internal-only commits. Returns a draft for…
Agent
Use proactively after any PM-artifact-producing skill completes (deliver-prd, foundation-meeting-recap, foundation-okr-writer, foundation-persona, foundation-lean-canvas, discover-interview-synthesis, define-problem-statement, define-hypothesis, deliver-edge-cases, deliver-user-stories, deliver-acceptance-criteria…
defendend/Claude-ast-index-search
Agent Claude Code
Use this agent to review a set of changes before they ship — staged/unstaged diff, a specific commit range, a PR description, or "the latest commit". The agent reads the diff against project rules in CLAUDE.md and .claude/rules/, runs the build and test suite, and reports what's good, what's wrong, and what's missing.…
Agent
A technical lead agent that reviews architecture and implementation plans for feasibility, maintainability, completeness, performance, security, and cost.
Agent Claude Code
Critical code quality inspector that challenges assumptions. MUST BE INVOKED before every git commit and git push. Demands proof via actual tests, identifies race conditions, unhandled errors, missing edge cases, and at least 3 potential failure points per change.
Agent
Autonomous task executor for spec-kit development. Executes a single task from tasks.md, verifies, commits, and signals completion.
Agent Claude Code
Owns the touchdesigner-mcp release from an unreleased diff to an opened development → main release PR. Use when the user asks to "release", "cut a release", "prepare vX.Y.Z", or "ship the pending changes". Orchestrates two skills — release-test-audit (gate: is the release diff tested?) then prepare-release…
Agent
Implements the planned change on a feature branch and addresses PR review comments. Handles single-repo and coordinated multi-service changes; keeps changes minimal and contract-safe.
Agent Cursor
CI helper for /monitor-ci. Fetches CI status, retrieves fix details, or updates self-healing fixes. Executes one MCP tool call and returns the result.
Agent Claude Code
Expert code review specialist. Reviews PRs for quality, security, and standards compliance. Use proactively after code changes or when a PR needs review.
Agent
Declare which directories hold an agent's runtime data, keep that data out of git, and export or import it on demand to move an agent between Trinity instances.
aj-geddes/claude-code-bmad-skills
Agent
PLANNING SUBAGENT — independently audits one or more planning artifacts and returns a structured verdict of PASS, CONCERNS, or FAIL with itemized findings. Designed for parallel deployment: spawn one auditor per artifact domain (requirements, architecture, stories) and let the orchestrator merge verdicts. Use when the…
Agent
Turn a code change into a prioritized browser-QA plan with Canary — read the git diff, infer the affected user-facing workflows, and suggest concrete flows and the checks that must hold, then optionally record them as a session with a report. Use when the user asks what to test for a change, wants to QA a…
Agent
Creates a git branch, commits a cask, and opens a PR to homebrew-cask.
Agent
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features one red-green-refactor slice at a time. No git commit allowed.
Agent Claude Code
Generates changelogs from git commit history and conversation context. Must be used immediately when the user asks to bump the version.
microsoft/skills-for-copilot-studio
Agent
You are an ALM (Application Lifecycle Management) specialist for Copilot Studio agents. You push, pull, and synchronize agent content between local YAML files and the Power Platform cloud.
Agent
Forward Deployed Engineering Strategist. Use for architecture planning, task decomposition, and team coordination of Salesforce Agentforce and platform implementations. Plans and delegates — never edits files directly. Spawns FDE team (engineer, experience specialist), cross-cutting roles (QA engineer, release…