claude-code-best-practice is a repository of agents, commands, skills, hooks, plugins, and configuration guidance for Claude Code. It helps developers organize repeatable workflows and apply agentic engineering practices, including in monorepos. The catalogue entries are its reusable Claude Code workflow components.
Borrowing it
Nothing to install: this file belongs to shanraisshan/claude-code-best-practice. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shanraisshan/claude-code-best-practice/main/.claude/commands/workflows/agent-collections.mdgit clone --depth 1 https://github.com/shanraisshan/claude-code-best-practiceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/shanraisshan/claude-code-best-practice/agent-collections)<a href="https://agentmods.dev/commands/shanraisshan/claude-code-best-practice/agent-collections"><img src="https://agentmods.dev/badge/commands/shanraisshan/claude-code-best-practice/agent-collections.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.01742 |
| Opus 5 | $0.00008 | $0.00871 |
| Sonnet 5 | $0.00003 | $0.00348 |
| Haiku 4.5 | $0.00002 | $0.00174 |
Grade A, and why
agent-collections scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow — Agent Collections
Update the AGENT COLLECTIONS table in README.md by researching the listed repos in parallel. Launch a research agent, merge results, present changes, update table if approved.
The Repos
| # | Repo | Owner |
|---|---|---|
| 1 | msitarzewski/agency-agents |
msitarzewski |
| 2 | VoltAgent/awesome-claude-code-subagents |
VoltAgent (curated awesome-list) |
When new agent-collection repos are discovered, add them here AND to the research prompt in Phase 1.
Table Format
The README table has these columns:
| Name | ★ | <img src="!/tags/a.svg" height="14"> |
- Name:
[Short Name](github-url)— use the repo's recognizable short name (e.g.,msitarzewski/agency-agents,awesome-claude-code-subagents). Use fullowner/repoonly if the bare name is ambiguous. - ★: Star count rounded to
k(e.g., 92k, 19k, 1.2k). Under 1000 show exact number. - Agent count: Just the number. For awesome-lists where agents are links not files, use
N+ (curated list)form.
Sort order: Sorted by stars descending (highest first).
Phase 0: Read Current State
Read these files:
README.md— the## 🤖 AGENT COLLECTIONStable (note current stars and agent counts)changelog/agent-collections/changelog.md— previous changelog entries (may not exist yet — create it on first run)
Phase 1: Launch Research Agent
Immediately spawn one development-workflows-research-agent covering all repos. (The existing research agent is generic — it counts agents/skills/commands/stars for any repo.)
Research these Claude Code agent-collection repositories. Each is primarily a library of subagent definition files (
.mdfiles defining agents), NOT a full workflow methodology.Repo 1: msitarzewski/agency-agents (https://github.com/msitarzewski/agency-agents) — agency-style subagent collection Repo 2: VoltAgent/awesome-claude-code-subagents (https://github.com/VoltAgent/awesome-claude-code-subagents) — curated awesome-list (links to external subagents, not all agents are stored as files in the repo)
For EACH repo, return:
- Stars — use GitHub API
https://api.github.com/repos/{owner}/{repo}, readstargazers_count. Round tok.- Agent count — count subagent definition
.mdfiles via the GitHub git tree API:https://api.github.com/repos/{owner}/{repo}/git/trees/HEAD?recursive=1and grep paths under conventional agent directories.
- For
msitarzewski/agency-agents: agents typically live underagents/,.claude/agents/, or category subdirectories. Count.mdfiles that look like subagent definitions (frontmatter withname:anddescription:). Exclude README/CHANGELOG/LICENSE/docs.- For
VoltAgent/awesome-claude-code-subagents: count the listed agents in README.md (e.g., bullets / table rows linking to external repos). Mark explicitly as "curated list, not files in repo".- If a repo has both a curated index AND its own agent files, report both numbers and explain.
- Notable changes — any significant additions or removals in the last 30 days?
Return structured report per repo:
REPO: msitarzewski/agency-agents STARS: <number>k (<exact>) AGENTS: <count> (<file pattern used, e.g., ".md files under agents/ via git tree">) NOTES: <anything unusual — flat layout vs categorized, README-only catalog, deprecated agents, curated-list disclaimer> CHANGES: <changes or "No significant changes"> CONFIDENCE: <0-1>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 159 lines · 16 tokens per session scan A 05250701d35e
agent-collections is a command published in the GitHub repository shanraisshan/claude-code-best-practice (65,687 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 1,742 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
plan-feature
Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.
retro-learn
Convert delivery findings into skill, eval, workflow, and documentation improvements.
version
Display current guide and Claude Code versions.
save
Save a key-value memory entry to persistent storage.
medical-necessity
Generate medical necessity letters citing chiropractic clinical guidelines for insurance authorization and appeals.