By peel
Orchestration skills for automated development lifecycle with multi-model support
Create a new Architecture Decision Record in docs/technical/decisions/. Asks what was decided and why, writes the ADR file.
Use to clean up stale beans and plan files — archives completed/scrapped beans and moves delivered plans to ignored directories.
Append an idea, tech debt item, or someday/maybe to docs/BACKLOG.md. Quick capture for things that aren't beans yet.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Challenge every aspect of this plan or design until we reach shared understanding. Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin for orchestrating a four-phase development lifecycle with a calibrated evaluator loop and multi-model support.
/fiddle:orchestrate <topic> chains four phases. Each phase is also a standalone skill.
DISCOVER /fiddle:discover — Scan project docs, research the ecosystem via external providers (Claude + Codex), and challenge scope assumptions until every branch is resolved.
DEFINE /fiddle:define — Brainstorm approaches, run a multi-model adversarial panel (Claude + Codex + Gemini), challenge the chosen design, then produce an implementation plan with sized beans.
DEVELOP /fiddle:develop — Execute beans via the evaluator loop: dispatch implementer → dispatch per-domain, per-provider evaluators → check thresholds → converge or iterate. Multi-domain evaluation with holistic cross-domain review when all tasks complete.
DELIVER /fiddle:deliver — Drift analysis via external providers (Claude + Codex), evaluator evolve step (calibration updates, antipattern capture, threshold tuning), update technical docs, close the epic.
[!NOTE] Any CLI that accepts a prompt on stdin works as a provider (Codex, Gemini, Copilot, etc). Configure per phase in
orchestrate.json.
The develop phase uses a calibrated evaluator loop: dispatch implementer → dispatch evaluators → check thresholds → converge or iterate. Script-enforced convergence (two consecutive passes required) with a dispatch budget that prevents infinite iteration.
Per-domain evaluation. Tasks spanning multiple domains (frontend + backend) get independent per-domain scoring. resolve-domains.sh maps task domains to evaluator templates. Domain-specific templates (frontend, backend) replace the general template for typed projects.
Runtime verification. Evaluators launch and interact with the running app via project-configured MCP tools (marionette, curl, go-dev-mcp) to gather evidence beyond static code review.
Multi-provider scoring. Multiple LLM providers evaluate each task for diversity of judgment. Conservative scoring (min across providers per dimension). Disagreements (spread >= 3) surfaced in eval logs.
Holistic review. After all tasks complete, a cross-domain integration review produces a spec coverage matrix and remediation loop for any gaps.
Calibration + evolve. Attended mode shows scorecards to humans before acting — corrections become calibration anchors in project-specific files. Antipattern files loaded by implementer and evaluator. The deliver evolve step encodes improvements for future runs.
| Skill | Description |
|---|---|
fiddle:brainstorm | Collaborative design dialogue with calibration anchor extraction. |
fiddle:write-plan | Generate implementation plan from a design spec. |
fiddle:evaluate | Evaluator protocol — score an implementation against domain template and criteria. |
fiddle:challenge | Walk the decision tree on any plan or design until shared understanding. |
fiddle:panel | Multi-model adversarial debate — Claude, Codex, Gemini argue positions and cross-review. |
fiddle:tdd | Test-driven development workflow. |
fiddle:verify | Run checks and verify implementation. |
fiddle:discover-docs | Socratic dialogue to bootstrap or review project docs. |
fiddle:deliver-docs | Post-ship doc updates — SYSTEM.md, ADRs, BACKLOG. |
fiddle:define-beans | Task sizing rules for decomposing plans into beans. |
fiddle:adr | Create an architecture decision record. |
fiddle:feedback | Append a user feedback signal. |
fiddle:backlog | Append an idea or tech debt item. |
fiddle:debug | Structured debugging workflow. |
Orchestrate reads orchestrate.json from the project root. All keys optional — defaults apply when omitted. See fiddle:orchestrate for the full reference.
npx claudepluginhub peel/fiddle --plugin fiddleStructured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
VGV Wingspan - AI-native workflows following Very Good Ventures best practices.
Conductor v3 — Multi-agent orchestration with Evaluate-Loop, parallel execution, Board of Directors, and bundled SupaConductor skills for Claude Code
AI-powered development tools for code review, research, design, and workflow automation.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.