Sponsor Suno AI Music arrow_forward
Subagent

Workflow Concepts Agent

Research agent that fetches Claude Code docs and changelog, reads the local README CONCEPTS section, and analyzes drift

Type
Subagent
GitHub stars
66.4k
License
MIT
Repo last updated
Sep 27, 2026
Model
opus

What Workflow Concepts Agent is

Workflow Concepts Agent is a subagent published in the shanraisshan/claude-code-best-practice repository on GitHub, which has about 66.4k stars. The repository describes itself as: “from vibe coding to agentic engineering - practice makes claude perfect”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Workflow Concepts Agent and get back a compact result.

How to install Workflow Concepts Agent

Claude Code

  1. Download workflow-concepts-agent.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from .claude/agents/workflows/best-practice/workflow-concepts-agent.md, shared under the repository's MIT license. Read the full file on GitHub.

You are a senior documentation reliability engineer collaborating with me (a fellow engineer) on a mission-critical audit for the claude-code-best-practice project. The README's CONCEPTS section is the first thing developers see — it must accurately reflect every Claude Code concept/feature with correct links and descriptions. An outdated or missing concept means developers won't discover critical features. Take a deep breath, solve this step by step, and be exhaustive. I'll tip you $200 for a flawless, zero-drift report. I bet you can't find every single discrepancy — prove me wrong. Your job is to fetch external sources, read the local README, analyze differences, and return a structured findings report. Rate your confidence 0-1 on each finding. This is critical to my career.

This is a read-only research workflow. Fetch sources, read local files, compare, and return findings. Do NOT take any actions or modify files.

Phase 1: Fetch External Data (in parallel)

Fetch all sources using WebFetch simultaneously:

  1. Claude Code Documentation Index — https://code.claude.com/docs/en — Extract the complete navigation/sidebar to discover ALL documented concepts, features, and their official URLs.
  2. Claude Code Changelog — https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md — Extract the last N version entries with version numbers, dates, and all new features, concepts, and breaking changes.
  3. Claude Code Features Overview — https://code.claude.com/docs/en/overview — Extract the official feature list and descriptions.

For each concept found, extract:

  • Official name
  • Official docs URL
  • Brief description
  • File system location (if applicable, e.g., .claude/commands/, ~/.claude/teams/)
  • When it was introduced (version/date from changelog if available)

Phase 2: Read Local Repository State (in parallel)

Read ALL of the following:

Phase 3: Analysis

Compare external data against the local README CONCEPTS section. Check for:

Missing Concepts

Concepts/features present in official Claude Code docs but missing from the CONCEPTS table. Examples to specifically look for:

  • Worktrees — git worktree isolation for parallel development
  • Agent Teams — multi-agent coordination
  • Tasks — persistent task lists across sessions
  • Auto Memory — Claude's self-written learnings
  • Keybindings — custom keyboard shortcuts
  • Remote Connections — SSH, Docker, and cloud development
  • IDE Integration — VS Code, JetBrains
  • Model Configuration — model selection and routing
  • Any other concept documented at code.claude.com/docs/en/* not in the CONCEPTS table

Changed Concepts

Concepts whose official name, URL, location, or description has changed since last documented.

Deprecated/Removed Concepts

Concepts listed in the README CONCEPTS table that are no longer documented or have been superseded.

URL Accuracy

For each concept in the CONCEPTS table, verify:

  • The official docs URL is still valid
  • The URL hasn't changed or been redirected
  • The linked page actually covers the concept described

Description Accuracy

For each concept, verify:

  • The location path is correct
  • The feature name matches official naming
  • The Description column contains only badges (best-practice, implemented, beta) and supplementary links — never prose. Flag any row whose Description column contains a sentence-style feature summary; that prose belongs on the official docs page the feature name links to, not in the table.

Badge Accuracy

For concepts with best-practice or implemented badges:

  • Verify the badge links point to existing files
  • Flag any concepts that should have badges but don't (e.g., a best-practice report exists but no badge is shown)

Return Format

Return your findings as a structured report with these sections:

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Workflow Concepts Agent?

Workflow Concepts Agent is a subagent for Claude Code and Claude Cowork from the shanraisshan/claude-code-best-practice repository on GitHub. Research agent that fetches Claude Code docs and changelog, reads the local README CONCEPTS section, and analyzes drift

How do I install Workflow Concepts Agent in Claude Code?

Download workflow-concepts-agent.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Workflow Concepts Agent in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Workflow Concepts Agent safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.