musterd-io/musterd
Agents that work as a team alongside you: named members across any harness, and every piece of work shows who did it and who accepted it.
field: unknown workflow: CI/CD & deployPlanning & specsDebuggingDocsFrontend & design runs claude in CI
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ claude mcp add whiteboard -e WHITEBOARD_LINKED_BOARDS=YOUR_WHITEBOARD_LINKED_BOARDS -- npx -y @musterd/whiteboard@0.1.0 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 whiteboard -e WHITEBOARD_LINKED_BOARDS=YOUR_WHITEBOARD_LINKED_BOARDS -- npx -y @musterd/whiteboard@0.1.0 $ npx degit musterd-io/musterd/.agents/skills/a-finding-is-not-a-fix-request .claude/skills/a-finding-is-not-a-fix-request $ npx degit musterd-io/musterd/.agents/skills/building-a-role-skill .claude/skills/building-a-role-skill $ npx degit musterd-io/musterd/.agents/skills/capture-rough-explore-once .claude/skills/capture-rough-explore-once $ npx degit musterd-io/musterd/.agents/skills/claims-ledger .claude/skills/claims-ledger $ npx degit musterd-io/musterd/.agents/skills/comms .claude/skills/comms $ npx degit musterd-io/musterd/.agents/skills/controls-in-force .claude/skills/controls-in-force $ npx degit musterd-io/musterd/.agents/skills/courier .claude/skills/courier $ npx degit musterd-io/musterd/.agents/skills/dated-and-falsifiable .claude/skills/dated-and-falsifiable $ npx degit musterd-io/musterd/.agents/skills/decision-records .claude/skills/decision-records $ npx degit musterd-io/musterd/.agents/skills/definition-of-done .claude/skills/definition-of-done $ npx degit musterd-io/musterd/.agents/skills/designer .claude/skills/designer $ npx degit musterd-io/musterd/.agents/skills/docs-that-catch-drift .claude/skills/docs-that-catch-drift $ npx degit musterd-io/musterd/.agents/skills/dreaming .claude/skills/dreaming $ npx degit musterd-io/musterd/.agents/skills/emitted-is-not-published .claude/skills/emitted-is-not-published $ npx degit musterd-io/musterd/.agents/skills/hooks-that-reach-the-model .claude/skills/hooks-that-reach-the-model $ npx degit musterd-io/musterd/.agents/skills/ios-engineer .claude/skills/ios-engineer $ npx degit musterd-io/musterd/.agents/skills/mast-checklist .claude/skills/mast-checklist $ npx degit musterd-io/musterd/.agents/skills/measure-agents-honestly .claude/skills/measure-agents-honestly $ npx degit musterd-io/musterd/.agents/skills/observer .claude/skills/observer $ npx degit musterd-io/musterd/.agents/skills/planner .claude/skills/planner $ npx degit musterd-io/musterd/.agents/skills/platform .claude/skills/platform $ npx degit musterd-io/musterd/.agents/skills/pre-registered-watch .claude/skills/pre-registered-watch $ npx degit musterd-io/musterd/.agents/skills/seat-workspace-identity .claude/skills/seat-workspace-identity $ npx degit musterd-io/musterd/.agents/skills/security-portable .claude/skills/security-portable $ npx degit musterd-io/musterd/.agents/skills/security .claude/skills/security $ npx degit musterd-io/musterd/.agents/skills/skill-home-and-provenance .claude/skills/skill-home-and-provenance $ npx degit musterd-io/musterd/.agents/skills/squig .claude/skills/squig $ npx degit musterd-io/musterd/.agents/skills/steward .claude/skills/steward $ npx degit musterd-io/musterd/.agents/skills/the-team-agreement .claude/skills/the-team-agreement $ npx degit musterd-io/musterd/.agents/skills/two-consumers .claude/skills/two-consumers
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| @musterd/whiteboard · "whiteboard" env: WHITEBOARD_LINKED_BOARDS | npm | 2.5k |
Skills (30)
a-finding-is-not-a-fix-requestbuilding-a-role-skillcapture-rough-explore-onceclaims-ledgercommscontrols-in-forcecourierdated-and-falsifiabledecision-recordsdefinition-of-donedesignerdocs-that-catch-driftdreamingemitted-is-not-publishedhooks-that-reach-the-modelios-engineermast-checklistmeasure-agents-honestlyobserverplannerplatformpre-registered-watchseat-workspace-identitysecurity-portablesecurityskill-home-and-provenancesquigstewardthe-team-agreementtwo-consumers
Similar rigs
trycourier/courier-skills
AI agent skill for building production-ready notifications across email, SMS, push, in-app, Slack, Teams, and WhatsApp. Covers deliverability, compliance, and growth patterns.
Pragmatist 3.2k tok · · Q0
SSFSKIM/designer
designer — a Claude Code plugin that gives Claude a working UI-design practice: commit to one stance, build on semantic tokens, use real content, hold an accessibility and taste floor. Includes an Essentialist persona distilled from Rams, B
Pragmatist 17.1k tok · · Q3
yschimke/compose-ai-tools
Helping the Agents Compose the Things
Pragmatist 4.5k tok · · Q15
AgriciDaniel/claude-code-essentials-vs-code
🚀 Claude Code & VS Code essentials — complete setup guide, extensions, slash commands, skills, and one-click install scripts for Windows.
Minimalist 848 tok · · Q0