sjdonado/dotfiles
macos/linux: terminal, editors, shell, AI harness
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add agent-browser -- agent-browser mcp $ claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest --autoConnect --userDataDir ~/.agent-browser/profile --no-usage-statistics --no-performance-crux $ claude mcp add ios-simulator -- npx -y ios-simulator-mcp $ npx degit sjdonado/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.
$ claude mcp add agent-browser -- agent-browser mcp $ claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest --autoConnect --userDataDir ~/.agent-browser/profile --no-usage-statistics --no-performance-crux $ claude mcp add ios-simulator -- npx -y ios-simulator-mcp
$ npx degit sjdonado/dotfiles/agents/skills/address-review .claude/skills/address-review $ npx degit sjdonado/dotfiles/agents/skills/agent-review .claude/skills/agent-review $ npx degit sjdonado/dotfiles/agents/skills/ask .claude/skills/ask $ npx degit sjdonado/dotfiles/agents/skills/create-ticket .claude/skills/create-ticket $ npx degit sjdonado/dotfiles/agents/skills/evidence .claude/skills/evidence $ npx degit sjdonado/dotfiles/agents/skills/feedback .claude/skills/feedback $ npx degit sjdonado/dotfiles/agents/skills/grill-me .claude/skills/grill-me $ npx degit sjdonado/dotfiles/agents/skills/handoff .claude/skills/handoff $ npx degit sjdonado/dotfiles/agents/skills/harness-audit .claude/skills/harness-audit $ npx degit sjdonado/dotfiles/agents/skills/harness-boostrap .claude/skills/harness-boostrap $ npx degit sjdonado/dotfiles/agents/skills/harness-restart .claude/skills/harness-restart $ npx degit sjdonado/dotfiles/agents/skills/land .claude/skills/land $ npx degit sjdonado/dotfiles/agents/skills/openspec-archive-change .claude/skills/openspec-archive-change $ npx degit sjdonado/dotfiles/agents/skills/openspec-explore .claude/skills/openspec-explore $ npx degit sjdonado/dotfiles/agents/skills/openspec-propose .claude/skills/openspec-propose $ npx degit sjdonado/dotfiles/agents/skills/openspec-sync-specs .claude/skills/openspec-sync-specs $ npx degit sjdonado/dotfiles/agents/skills/openspec-update-change .claude/skills/openspec-update-change $ npx degit sjdonado/dotfiles/agents/skills/openspec-verify-change .claude/skills/openspec-verify-change $ npx degit sjdonado/dotfiles/agents/skills/ponytail .claude/skills/ponytail $ npx degit sjdonado/dotfiles/agents/skills/proto .claude/skills/proto $ npx degit sjdonado/dotfiles/agents/skills/research .claude/skills/research $ npx degit sjdonado/dotfiles/agents/skills/triage .claude/skills/triage $ npx degit sjdonado/dotfiles/agents/skills/verification .claude/skills/verification $ npx degit sjdonado/dotfiles/agents/skills/yolo .claude/skills/yolo
$ 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.com/sjdonado/dotfiles/main/agents/skills/agent-review/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.com/sjdonado/dotfiles/main/agents/skills/create-ticket/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>.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/sjdonado/dotfiles/main/agents/skills/grill-me/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>-audit/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-boostrap/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-restart/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>-archive-change/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-explore/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-propose/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-sync-specs/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-update-change/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-verify-change/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>.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>.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>.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 *)"
]
}
} MCP servers (4)
| server | source | est. tokens |
|---|---|---|
| agent-browser | binary | 2.5k |
| Chrome DevTools MCP · "chrome-devtools" | npm | 9.0k |
| ios-simulator-mcp · "ios-simulator" | npm | 2.5k |
| git-bug | local / custom | 2.5k |
Skills (24)
address-reviewagent-reviewaskcreate-ticketevidencefeedbackgrill-mehandoffharness-auditharness-boostrapharness-restartlandopenspec-archive-changeopenspec-exploreopenspec-proposeopenspec-sync-specsopenspec-update-changeopenspec-verify-changeponytailprotoresearchtriageverificationyolo
Subagents (24)
| address-review | Address open PR review threads, reply only inside those threads, and fix red CI or an outdated branch. Use for "address the review comments", "CI is red on my PR". |
| agent-review | Agent-initiated adversarial review of a diff before pushing. Spawns blind reviewers told to assume the code is wrong, then triages their findings. Use when a workflow needs to check its own work, not |
| ask | Answer one focused question. Investigate if needed, answer directly, no changes until approved. Use for "what does X do", "why does Y happen", or one bounded question. |
| create-ticket | Draft a clear, scoped ticket from a request or research findings, then create it via the tracker MCP after confirmation. Use for "create a ticket for this", "file this", "make an issue". |
| evidence | Challenge a load-bearing claim with production data instead of asserting it. Defines the falsifiable-prediction protocol, the kill query, a capability-based source map, query budgets, and the no-fabri |
| feedback | Apply bullet-list feedback locally on the current PR's branch, report the checks, and publish the batch only once the user approves it. Use for changes, corrections, or follow-up work on an open PR. |
| grill-me | A relentless interview that attacks the load-bearing assumptions in a plan or design before they become expensive. Two modes, interactive for a human-driven grilling and self-grill for resolving your |
| handoff | Compact the current conversation into a handoff document for another agent to pick up. |
| harness-audit | Audit how the agent harness performed in one project from its residue (branch notes, PR bodies, OpenSpec changes, session transcripts) and recommend fixes. Read-only. Use for "how is the harness doing |
| harness-boostrap | Audit, create, or update a project's AGENTS.md instruction files from repository evidence so coding agents can navigate, change, and verify the project. Use for "set up project agent instructions", "a |
| harness-restart | Restart the Claude Code or OpenCode processes running in herdr panes so they pick up a newer binary, keeping each conversation by resuming its session id. Use when an agent binary has updated and long |
| land | After verifying a PR actually merged, close its branch note and, when an OpenSpec change exists, verify, sync, and archive its specs. An unmerged PR stops the workflow with the note left awaiting merg |
| openspec-archive-change | Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete. |
| openspec-explore | Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change. |
| openspec-propose | Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for i |
| openspec-sync-specs | Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change. |
| openspec-update-change | Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reco |
| openspec-verify-change | Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving. |
| ponytail | Prefer the smallest correct implementation when writing, fixing, refactoring or reviewing code, including prototype code and implementation-level dependency choices. Also applies to requests for lazy |
| proto | Prototype through small human-tested iterations, then hand a requirements ledger to yolo or kill the premise. Use when implementation requirements are still open, such as "implement this", "go build i |
| research | Deeply investigate a question or claim and return a sourced conclusion without making changes. Use for "look into X", "is it true that", "dig into whether". |
| triage | From a ticket or a production error signal, understand the request, challenge it with data, and propose an approach with tradeoffs (no implementation). Use for a pasted ticket, "triage this", "how sho |
| verification | Drive a change's checks to green and report back, in a subagent or in the current session. Runs the oracle ladder, fixes what the change broke, and returns a verdict. Use when a workflow needs its che |
| yolo | Autonomous requirements-to-PR. Clarify once, understand deeply, implement lazily, then drive every check green with no further input. Use for "yolo it", "open a PR", or work whose agreement meets Publ |
Similar rigs
Fission-AI/OpenSpec
Spec-driven development (SDD) for AI coding assistants.
Skill Collector 1.5k tok ·
pabloimrik17/dotfiles
—
Skill Collector 1.4k tok ·
Artexis10/endstate
Open-source engine behind Endstate: reinstall your apps and restore your settings on a fresh machine from one file. Windows via winget (Linux/macOS in progress). Go, Apache 2.0.
Skill Collector 2.5k tok ·
ValorVie/custom-skills
Automated AI dev environment setup CLI with curated Skills collection for Claude Code and other AI coding assistants.
Orchestrator 6.2k tok ·