JasonWarrenUK/goblin-mode
Three goblins in a trenchcoat pretending to be a senior developer. Claude Code config shaped by ADHD, friction, and spite.
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 JasonWarrenUK/goblin-mode/.claude ./rig-goblin-mode # 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 JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/claim .claude/skills/claim $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/create-interview .claude/skills/create-interview $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/create .claude/skills/create $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/dashboard .claude/skills/dashboard $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/maintain .claude/skills/maintain $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/migrate .claude/skills/migrate $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/next-group .claude/skills/next-group $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/next-suggest .claude/skills/next-suggest $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/review .claude/skills/review $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/update-devs .claude/skills/update-devs $ npx degit JasonWarrenUK/goblin-mode/marketplace/roadmap/skills/update-tasks .claude/skills/update-tasks $ npx degit JasonWarrenUK/goblin-mode/skills/artefact-audit .claude/skills/artefact-audit $ npx degit JasonWarrenUK/goblin-mode/skills/artefact-conventions .claude/skills/artefact-conventions $ npx degit JasonWarrenUK/goblin-mode/skills/artefact-intro .claude/skills/artefact-intro $ npx degit JasonWarrenUK/goblin-mode/skills/artefact-playground .claude/skills/artefact-playground $ npx degit JasonWarrenUK/goblin-mode/skills/artefact-research .claude/skills/artefact-research $ npx degit JasonWarrenUK/goblin-mode/skills/asset-card .claude/skills/asset-card $ npx degit JasonWarrenUK/goblin-mode/skills/asset-conventions .claude/skills/asset-conventions $ npx degit JasonWarrenUK/goblin-mode/skills/asset-demo .claude/skills/asset-demo $ npx degit JasonWarrenUK/goblin-mode/skills/asset-pdf .claude/skills/asset-pdf $ npx degit JasonWarrenUK/goblin-mode/skills/asset-shot .claude/skills/asset-shot $ npx degit JasonWarrenUK/goblin-mode/skills/asset-still .claude/skills/asset-still $ npx degit JasonWarrenUK/goblin-mode/skills/branch-integrate .claude/skills/branch-integrate $ npx degit JasonWarrenUK/goblin-mode/skills/branch-qa_review .claude/skills/branch-qa_review $ npx degit JasonWarrenUK/goblin-mode/skills/branch-rename .claude/skills/branch-rename $ npx degit JasonWarrenUK/goblin-mode/skills/branch-worktree .claude/skills/branch-worktree $ npx degit JasonWarrenUK/goblin-mode/skills/clod-approach-stud .claude/skills/clod-approach-stud $ npx degit JasonWarrenUK/goblin-mode/skills/clod-approach-writing_style .claude/skills/clod-approach-writing_style $ npx degit JasonWarrenUK/goblin-mode/skills/clod-config-skill_conventions .claude/skills/clod-config-skill_conventions $ npx degit JasonWarrenUK/goblin-mode/skills/clod-lens-empathy .claude/skills/clod-lens-empathy $ npx degit JasonWarrenUK/goblin-mode/skills/clod-lens-ethics .claude/skills/clod-lens-ethics $ npx degit JasonWarrenUK/goblin-mode/skills/clod-lens-scope .claude/skills/clod-lens-scope $ npx degit JasonWarrenUK/goblin-mode/skills/clod-role-api_designer .claude/skills/clod-role-api_designer $ npx degit JasonWarrenUK/goblin-mode/skills/clod-role-data_ontologist .claude/skills/clod-role-data_ontologist $ npx degit JasonWarrenUK/goblin-mode/skills/clod-role-domain_modeller .claude/skills/clod-role-domain_modeller $ npx degit JasonWarrenUK/goblin-mode/skills/clod-role-frontend_styler .claude/skills/clod-role-frontend_styler $ npx degit JasonWarrenUK/goblin-mode/skills/clod-role-git_manager .claude/skills/clod-role-git_manager $ npx degit JasonWarrenUK/goblin-mode/skills/clod-role-testing_obsessive .claude/skills/clod-role-testing_obsessive $ npx degit JasonWarrenUK/goblin-mode/skills/clod-stack-cypher .claude/skills/clod-stack-cypher $ npx degit JasonWarrenUK/goblin-mode/skills/clod-stack-gum .claude/skills/clod-stack-gum
$ curl -fsSL --create-dirs -o .claude/agents/design-reviewer.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/design-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/implementation-planner.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/implementation-planner.md $ curl -fsSL --create-dirs -o .claude/agents/project-context-loader.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/project-context-loader.md $ curl -fsSL --create-dirs -o .claude/agents/scope-guard.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/scope-guard.md $ curl -fsSL --create-dirs -o .claude/agents/session-closer.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/session-closer.md $ curl -fsSL --create-dirs -o .claude/agents/session-orchestrator.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/session-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/ship-checker.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/ship-checker.md $ curl -fsSL --create-dirs -o .claude/agents/task-sync.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/task-sync.md $ curl -fsSL --create-dirs -o .claude/agents/test-gap-scanner.md https://raw.githubusercontent.com/JasonWarrenUK/goblin-mode/main/agents/test-gap-scanner.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (70)
Roadmap: ClaimRoadmap: ProposeRoadmap: CreateArtefacts: Create RoadmapRoadmap: MaintainRoadmap: MigrateNext Task: GroupNext Task: SuggestRoadmap: ReviewRoadmap: Assign DevsRoadmap: Add TaskArtefact: Render AuditArtefact: Design ConventionsArtefacts: Introduce RepoArtefact: PlaygroundArtefact: ResearchAsset: CardAsset: ConventionsAsset: DemoAsset: PDFAsset: ShotAsset: StillBranch: IntegrateBranch: QA ReviewBranch: Rename If NeededBranch: WorktreeApproach: StudApproach: Writing StyleConfig: Skill ConventionsLens: EmpathyLens: EthicsLens: ScopeRole: API DesignerRole: Data OntologistRole: Domain ModellerRole: Frontend StylerRole: Git ManagerRole: Testing ObsessiveStack: CypherStack: GumStack: OpenTUIStack: SvelteCommit: BatchCommit: OneDo: MinimaDo: StudDocs: ChangelogDocs: ReadmeDossier: RecordHUD: Claude Code ReleasesHUD: ProfilesHUD: Prose HealthHUD: What's NewHUD: WorktreesImport: Scaffold from ArtefactNext Task: ShipPR: CreatePR: Handle ReviewPR: LandPR: Review (Dry Run)PR: ReviewPR: UpdateProject: Audit DependenciesProject: Tag VersionRed: BranchRed: Docskill-creatorTheme: FactoryTheme: TargetTrack: Claude Code Pain Points
Subagents (9)
| design-reviewer model: opus | Use this agent to review a proposed feature or solution against design values before implementation. Evaluates sophistication (depth of understanding), empowerment (serves the user), robustness (handl |
| implementation-planner model: opus | Use this agent when you need to break down a development request into a detailed, actionable implementation plan. Examples: <example>Context: User wants to add a new feature to their project. user: 'I |
| project-context-loader model: sonnet | Use this agent when switching between projects (Iris, Rhea, Theia, etc.) to quickly rebuild context. Synthesises recent git history, architectural decisions, current work state and key patterns to min |
| scope-guard model: sonnet | Use this agent to proactively monitor scope during planning and implementation. Detects when plans grow beyond the original ask, when branches touch unrelated files and when step counts signal complex |
| session-closer model: sonnet | Use this agent at the end of a session to capture state for next time. Summarises accomplishments, notes uncommitted work, updates task-tracker status, generates a work record entry and writes a hando |
| session-orchestrator model: sonnet | Use this agent at the start of a session to build a work plan. Combines project context, task-tracker state, open branches and roadmap priorities into a ranked list of 2-3 things to work on. Primes th |
| ship-checker model: opus | Use this agent before shipping to run a multi-dimensional quality check. Combines branch assessment, test gap analysis, documentation staleness, breaking change detection and task-tracker validation i |
| task-sync model: sonnet | Use this agent to keep task tracker state consistent with git/codebase state. Adapts to whatever task source the project uses (see docs/reference/task-trackers/). Detects branch checkouts, PR creation |
| test-gap-scanner model: sonnet | Use this agent to identify code that should have tests but doesn't, using risk-based prioritisation from the clod-role-testing_obsessive skill. Analyses branch diff against main, applies impact × comp |
Similar rigs
lambdalisue/dotfiles
🩳 My personal dotfiles
Skill Collector 10.2k tok ·
kevinreber/claude-code-configs
General Claude Code configs I use
Orchestrator 6.4k tok ·
ahmedelgabri/dotfiles
~ 🍭 ~
Skill Collector 7.8k tok ·
AYESHAKHAN101/personal-ai-employee
Personal AI Employee – Bronze Tier autonomous AI system that monitors files, extracts tasks, and executes workflows using Claude Code skills.
Skill Collector 5.8k tok ·