drn/dots
:new_moon: Obsessively curated dotfiles.
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 drn/dots/.claude ./rig-dots # inspect, then merge into .claude/ 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 drn/dots/agents/skills/address-comments .claude/skills/address-comments $ npx degit drn/dots/agents/skills/amend .claude/skills/amend $ npx degit drn/dots/agents/skills/bash-tool-path .claude/skills/bash-tool-path $ npx degit drn/dots/agents/skills/bisect .claude/skills/bisect $ npx degit drn/dots/agents/skills/ci-investigate .claude/skills/ci-investigate $ npx degit drn/dots/agents/skills/combine-prs .claude/skills/combine-prs $ npx degit drn/dots/agents/skills/contest .claude/skills/contest $ npx degit drn/dots/agents/skills/cross-agent .claude/skills/cross-agent $ npx degit drn/dots/agents/skills/debug .claude/skills/debug $ npx degit drn/dots/agents/skills/deploy-audit .claude/skills/deploy-audit $ npx degit drn/dots/agents/skills/deploy-validate .claude/skills/deploy-validate $ npx degit drn/dots/agents/skills/deploy .claude/skills/deploy $ npx degit drn/dots/agents/skills/deps .claude/skills/deps $ npx degit drn/dots/agents/skills/dev .claude/skills/dev $ npx degit drn/dots/agents/skills/devils-advocate .claude/skills/devils-advocate $ npx degit drn/dots/agents/skills/dream .claude/skills/dream $ npx degit drn/dots/agents/skills/eli5 .claude/skills/eli5 $ npx degit drn/dots/agents/skills/email .claude/skills/email $ npx degit drn/dots/agents/skills/equip .claude/skills/equip $ npx degit drn/dots/agents/skills/explore .claude/skills/explore $ npx degit drn/dots/agents/skills/guard .claude/skills/guard $ npx degit drn/dots/agents/skills/handoff .claude/skills/handoff $ npx degit drn/dots/agents/skills/improve .claude/skills/improve $ npx degit drn/dots/agents/skills/knowledge .claude/skills/knowledge $ npx degit drn/dots/agents/skills/learn .claude/skills/learn $ npx degit drn/dots/agents/skills/logo .claude/skills/logo $ npx degit drn/dots/agents/skills/loop .claude/skills/loop $ npx degit drn/dots/agents/skills/markdown-preview .claude/skills/markdown-preview $ npx degit drn/dots/agents/skills/merge .claude/skills/merge $ npx degit drn/dots/agents/skills/migrate .claude/skills/migrate $ npx degit drn/dots/agents/skills/notion-address-comments .claude/skills/notion-address-comments $ npx degit drn/dots/agents/skills/notion .claude/skills/notion $ npx degit drn/dots/agents/skills/orchestrate-stack .claude/skills/orchestrate-stack $ npx degit drn/dots/agents/skills/orchestrate .claude/skills/orchestrate $ npx degit drn/dots/agents/skills/pdf .claude/skills/pdf $ npx degit drn/dots/agents/skills/perf .claude/skills/perf $ npx degit drn/dots/agents/skills/plan .claude/skills/plan $ npx degit drn/dots/agents/skills/plannotator-annotate .claude/skills/plannotator-annotate $ npx degit drn/dots/agents/skills/plannotator-compound .claude/skills/plannotator-compound $ npx degit drn/dots/agents/skills/plannotator-last .claude/skills/plannotator-last
$ curl -fsSL --create-dirs -o .claude/agents/code-analyst.md https://raw.githubusercontent.com/drn/dots/master/agents/custom/code-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/investigator.md https://raw.githubusercontent.com/drn/dots/master/agents/custom/investigator.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/drn/dots/master/agents/custom/verifier.md $ curl -fsSL --create-dirs -o .claude/agents/phase-protocol.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/_shared/resources/phase-protocol.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/address-comments/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/amend/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/bash-tool-path/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/bisect/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/ci-investigate/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/combine-prs/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/contest/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/cross-agent/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/debug/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/deploy-audit/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/deploy-validate/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/deploy/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/deps/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/dev/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/BRIEFINGS.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/CODE_REVIEW.md https://raw.githubusercontent.<redacted>_REVIEW.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/devils-advocate/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/dream/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/eli5/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/email/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/equip/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/explore/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/guard/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/handoff/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/improve/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/argus-kb.md https://raw.githubusercontent.<redacted>-kb.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.com/drn/dots/master/agents/skills/learn/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/logo/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/loop/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/markdown-preview/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/merge/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/migrate/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/notion-address-comments/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/notion/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/drn/dots/master/agents/skills/orchestrate-stack/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 (67)
address-commentsamendbash-tool-pathbisectci-investigatecombine-prscontestcross-agentdebugdeploy-auditdeploy-validatedeploydepsdevdevils-advocatedreameli5emailequipexploreguardhandoffimproveknowledgelearnlogoloopmarkdown-previewmergemigratenotion-address-commentsnotionorchestrate-stackorchestratepdfperfplanplannotator-annotateplannotator-compoundplannotator-lastplannotator-reviewplannotator-setup-goalplannotator-visual-explainerpolishprprioritizeprompt-summaryprunerebasereleaserereview-looprereviewretroreviewscaffoldscreenshotshipskill-usageslackslidesspikesquashstandupswarmttswrapupwrite-skill
Subagents (78)
| code-analyst | Code quality analyzer that checks codebases against specialized checklists. Use for parallel code analysis across quality dimensions (structure, design, smells, idioms, security, regressions). |
| investigator | Evidence-based investigator that pursues hypotheses or research angles, debates peers, and converges on truth. Use for debugging (hypothesis-driven) and codebase exploration (angle-based research). |
| verifier | Test runner and implementation evaluator that verifies code correctness, identifies regressions, and scores implementations. Use for test verification, regression checking, and comparative evaluation |
| phase-protocol | — |
| address-comments | Walk every unresolved review thread on a PR, triage each one, reply with a rationale of whether or not the comment will be acted upon, make the code change if warranted, and mark the thread resolved. |
| amend | Amend the last git commit with a useful, descriptive message. Use when you want to rewrite a commit message, amend commit description, or improve the last commit message. |
| bash-tool-path | Safely add a directory to Claude Code's Bash tool PATH. Use when a binary runs in your terminal but is "command not found" inside Claude Code's Bash tool, when adding a directory to PATH for Claude Co |
| bisect | Find which commit introduced a bug using git bisect with automatic test verification. Use when tracking down which commit introduced a bug. |
| ci-investigate | Investigate flaky CI failures across multiple workflow runs to identify patterns, categorize root causes, and propose fixes. Use when asked to investigate CI failures, find flaky tests, diagnose test |
| combine-prs | Compare two competing PRs implementing the same feature, identify strengths of each, and combine the best parts into a single branch. Use when comparing PRs, combining implementations, cherry-picking |
| contest | Competing implementations with judge evaluation. Use when comparing multiple approaches, picking the best solution, or running a bake-off. |
| cross-agent | Set up cross-agent skill infrastructure so skills work across Claude Code, OpenAI Codex, and GitHub Copilot. Use for multi-agent compatibility, skill migration, cross-agent sync. |
| debug | Multi-agent competing hypotheses debugging. Use when stuck on a bug, need root cause analysis, or want competing debug theories. |
| deploy-audit | Audit every commit pending between a base branch and a deployed branch/tag for deploy risk (migrations, config/secret wiring completeness, feature-flag defaults, schema parity), then open the GitHub c |
| deploy-validate | Validate a deploy after it lands — CI status, rollout health, error tracking, and monitoring/alerting — correlating every finding against the deploy's start time to separate genuine regressions from p |
| deploy | Deploy latest master to production with a version tag. Use when releasing to production or tagging a deploy. |
| deps | Audit outdated dependencies, check for vulnerabilities, and upgrade with test verification. Use for dependency audits, security checks, or upgrading packages. |
| dev | Multi-agent iterative development with parallel testing and code review. Use for building features, implementing changes, or coding tasks that need testing and review. |
| BRIEFINGS | — |
| CODE_REVIEW | — |
| devils-advocate | Execute the /devils-advocate workflow shared across Codex, Claude Code, and Copilot in this repository. Use when you want to stress-test ideas, challenge assumptions, or play devil's advocate. |
| dream | Scheduled KB maintenance — ingest meetings and Claude Code/Codex JSONL sessions, synthesize raw notes into existing topical docs (decisions, people changes, conventions), resolve conflicts, age out st |
| eli5 | Explain any topic in the simplest possible terms using analogies and everyday examples. Use when the user says "explain like I'm 5", "eli5", "explain simply", "dumb it down", or "explain in simple ter |
| Search and read Gmail messages. Use when looking up emails, reading email threads, or checking inbox labels. | |
| equip | Analyze a spec, PRD, or codebase to identify missing skills and agents, propose them, then write them. Use for skill gap analysis, agent gap analysis, bootstrapping agent capabilities from a spec, or |
| explore | Multi-agent parallel research with peer-challenged synthesis. Use for deep research, codebase exploration, or investigating how something works. |
| guard | Pre-commit safety check for secrets, security antipatterns, and test breakage. Use for pre-commit checks, secret scanning, or verifying test safety. |
| handoff | Generate a handoff prompt to pass context to another agent thread. Use when switching repos, handing off work, or sharing context between agents. |
| improve | Improve skills, capture context & knowledge. Use for skill iteration, capturing learnings, or upgrading agent context. |
| argus-kb | — |
| knowledge | Initialize or update a project knowledge base for durable cross-session knowledge capture. Use for setting up or updating project knowledge bases. |
| learn | Alias for /improve — improve skills, capture context & knowledge. Use for skill iteration, capturing learnings, or upgrading agent context. |
| logo | Generate SVG logo alternatives with side-by-side comparison. Use when creating logos, branding, or project icons. |
| loop | Run a prompt on a recurring interval using a blocking sleep loop. Use for polling CI, babysitting deploys, monitoring logs, periodic checks, or scheduled task execution. |
| markdown-preview | Render a Markdown file to GitHub-flavored HTML and open a styled local preview (light + dark) in the browser. Use when the user wants to preview markdown, see how a README renders on GitHub, check tha |
| merge | Merge current branch to the default branch via GitHub PR merge. Use when ready to merge a PR or land a branch. |
| migrate | Multi-agent codebase migration with module ownership. Use for large refactors, API upgrades, framework migrations, or bulk code changes. |
| notion-address-comments | Iterate on a Notion page against its open inline comments — read each unresolved thread, edit the page to address it, and reply with a short summary of the change. Use when the user asks to address th |
| notion | Read Notion pages and databases using MCP tools. Use when looking up Notion content, reading pages, or querying databases. |
| orchestrate-stack | Orchestrate a stack of dependent Argus tasks that produce a chain of stacked PRs. Use when the user has a multi-milestone plan that should land as N PRs where each branches off the previous. Decompose |
Slash commands (3)
/openspec/apply/openspec/archive/openspec/proposal
Similar rigs
wangqiqi/cursor-ai
无关用户， 无关系统， 无关项目，开箱复制即用！ code faster, code better;
Skill Collector 2.8k tok ·
nejcfurh/nejcfurh-claude
Personal global Claude Code configuration — rules, skills, agents, hooks, and settings that apply to every project.
Fort Knox 5.3k tok ·
damilola-elegbede-org/claude-config
Configurations Files for Claude
YOLO Cowboy 35.2k tok ·
edlitmus/claude-dotfiles
—
Skill Collector 24.7k tok ·