benmatselby/dotfiles
⊙ All the dotfiles needed to make the world a better place
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit benmatselby/dotfiles/agents ./rig-dotfiles/agents MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit benmatselby/dotfiles/agents/skills/code-review-focus .claude/skills/code-review-focus $ npx degit benmatselby/dotfiles/agents/skills/code-review .claude/skills/code-review $ npx degit benmatselby/dotfiles/agents/skills/datadog-investigation .claude/skills/datadog-investigation $ npx degit benmatselby/dotfiles/agents/skills/dependency-evaluator .claude/skills/dependency-evaluator $ npx degit benmatselby/dotfiles/agents/skills/draft-pr .claude/skills/draft-pr $ npx degit benmatselby/dotfiles/agents/skills/git-log .claude/skills/git-log $ npx degit benmatselby/dotfiles/agents/skills/github-issue-analyzer .claude/skills/github-issue-analyzer $ npx degit benmatselby/dotfiles/agents/skills/log-session .claude/skills/log-session $ npx degit benmatselby/dotfiles/agents/skills/poc .claude/skills/poc $ npx degit benmatselby/dotfiles/agents/skills/proofread-blog .claude/skills/proofread-blog $ npx degit benmatselby/dotfiles/agents/skills/resolve-pr-comments .claude/skills/resolve-pr-comments $ npx degit benmatselby/dotfiles/agents/skills/summarise-diary .claude/skills/summarise-diary
$ curl -fsSL --create-dirs -o .claude/agents/log-session.md https://raw.githubusercontent.<redacted>-session.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-review-focus/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-review/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-investigation/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-evaluator/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-pr/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/benmatselby/dotfiles/main/agents/skills/git-log/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-issue-analyzer/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/benmatselby/dotfiles/main/agents/skills/log-session/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-blog/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-pr-comments/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-diary/SKILL.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (12)
bms:code-review-focusbms:code-reviewbms:datadog-investigationbms:dependency-evaluatorbms:draft-prbms:git-log-summarybms:github-issue-analyzerbms:log-sessionbms:pocbms:proofread-blogbms:resolve-pr-commentsbms:summarise-diary
Subagents (13)
| log-session | Log a summary of this OpenCode session to today's work diary |
| bms:code-review-focus | Provide a summary focus of the code to highlight what I should understand deeply from this code |
| bms:code-review | Performs a harsh but constructive code review of a file or set of files. Use when asked to review, critique, or give feedback on code quality. |
| bms:datadog-investigation | Investigate platform issues in Datadog. |
| bms:dependency-evaluator | Evaluates whether a GitHub repository (tool, library, or framework) is worth adopting for the current project. Use when given a GitHub repo URL to assess as a potential dependency or tool. |
| bms:draft-pr | Create a draft pull request for the current branch. Summarises the diff, fills in any PR templates, and opens the PR via the gh CLI. |
| bms:git-log-summary | Provides a summary of the git log for the past period of time. Use when asked to provide a git log summary. |
| bms:github-issue-analyzer | Analyzes a GitHub issue by fetching its details and exploring the relevant codebase to identify the root cause and suggest solutions. Use when given a GitHub issue URL to investigate. |
| bms:log-session | Log a one-line summary of the current OpenCode session to today's work diary under the Completed section |
| bms:poc | Creates a proof of concept implementation. Provides the smallest working solution to validate an idea, with no tests and minimal production concerns. |
| bms:proofread-blog | Proofreads a blog post for clarity, balance, and general quality. Use when asked to proofread, review, or critique a blog post or article. |
| bms:resolve-pr-comments | Review open review comments on a GitHub PR, agree a fix with the user, apply the change, commit, push, and mark the thread resolved. |
| bms:summarise-diary | Summarize diary entries for a given time period |
Similar rigs
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Orchestrator 2.6k tok ·
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
Orchestrator 14.5k tok ·
alirezarezvani/claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, complian
Orchestrator 48.5k tok ·
czlonkowski/n8n-mcp
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
Orchestrator 3.8k tok ·