c/claude-archeflow-plugin
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: ArcheFlow — multi-agent orchestration plugin for Claude Code

Browse Source 
Zero-dependency Claude Code plugin using Jungian archetypes as
behavioral protocols for multi-agent orchestration.

- 7 archetypes (Explorer, Creator, Maker, Guardian, Skeptic, Trickster, Sage)
- ArcheHelix: rising PDCA quality spiral with feedback loops
- Shadow detection: automatic dysfunction recognition and correction
- 3 built-in workflows (fast, standard, thorough)
- Autonomous mode: unattended overnight sessions with full visibility
- Custom archetypes and workflows via markdown/YAML
- SessionStart hook for automatic bootstrap
- Examples for feature implementation and security review
This commit is contained in:
Christian Nennemann
2026-04-02 16:37:23 +00:00
parent 071724a568
commit a6fa708f8b
24 changed files with 1929 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
skills/using-archeflow/SKILL.md Normal file
View File

@@ -0,0 +1,96 @@
---
name: using-archeflow
description: Use at session start when implementing features, reviewing code, debugging, or any task that benefits from multiple perspectives. This skill activates ArcheFlow multi-agent orchestration with Jungian archetypes.
---
# ArcheFlow — Multi-Agent Orchestration
You have ArcheFlow installed. ArcheFlow gives you a structured way to coordinate multiple agents through quality cycles using Jungian archetypes as behavioral protocols.
## How It Works
Instead of one agent doing everything, ArcheFlow splits work across **archetypal roles** that think differently:
| Archetype | Thinks Like | Produces |
|-----------|-------------|----------|
| **Explorer** | Researcher — gathers context, reads code, maps dependencies | Research findings |
| **Creator** | Architect — designs the solution, writes the plan | Proposal with confidence score |
| **Maker** | Builder — implements code from the plan | Working code + tests |
| **Guardian** | Security reviewer — finds risks, checks reliability | Risk assessment (approve/reject) |
| **Skeptic** | Devil's advocate — challenges assumptions | Counterarguments + alternatives |
| **Trickster** | Adversarial tester — finds edge cases, breaks things | Edge case challenges |
| **Sage** | Senior reviewer — holistic quality judgment | Quality report (approve/reject) |
## The ArcheHelix — Rising Quality Spiral
Work flows through **Plan → Do → Check → Act** in a rising spiral called the **ArcheHelix**. Each cycle incorporates feedback from the previous one:
```
Plan: Explorer researches → Creator proposes solution
↓
Do: Maker implements in isolated worktree
↓
Check: Guardian + Skeptic + Sage review in parallel
↓
Act: All approved? → Merge and done
Issues found? → Spiral up: feed back to Plan, cycle again
```
The helix ensures that every iteration is better than the last — not just repeated.
## When to Use ArcheFlow
**USE IT when:**
- Implementing features that span multiple files or concerns
- The task has security, performance, or reliability implications
- You'd benefit from a code review before merging
- Debugging requires testing multiple hypotheses in parallel
- The user asks for thorough, multi-perspective work
**SKIP IT when:**
- Single-file typo fix or formatting change
- User explicitly wants quick-and-dirty
- Task is purely informational (reading, explaining)
## Built-in Workflows
| Workflow | Phases | Cycles | Best For |
|----------|--------|--------|----------|
| `fast` | Creator → Maker → Guardian | 1 | Bug fixes, small changes |
| `standard` | Explorer + Creator → Maker → Guardian + Skeptic + Sage | 2 | Features, refactors |
| `thorough` | Explorer + Creator → Maker → All 4 reviewers | 3 | Security-critical, public APIs |
## How to Run an Orchestration
When a task matches, use the **archeflow:orchestration** skill. It will guide you through:
1. Selecting the right workflow
2. Spawning archetype agents (using the Agent tool with worktree isolation)
3. Managing the PDCA cycle
4. Merging results
## Shadow Detection
Each archetype has a **shadow** — a destructive inversion of its strength:
| Archetype | Shadow | Symptom |
|-----------|--------|---------|
| Explorer | Rabbit hole | Endless research, no synthesis |
| Creator | Perfectionism | Infinite revision, never ships |
| Guardian | Paranoia | Blocks everything, zero risk tolerance |
| Skeptic | Paralysis | Questions everything, approves nothing |
| Maker | Cowboy coding | Ships without tests or review |
| Trickster | Chaos | Breaks things without constructive purpose |
| Sage | Bloat | Over-documents, under-delivers |
If you detect shadow behavior in an agent's output, flag it and course-correct.
## Other ArcheFlow Skills
- **archeflow:orchestration** — Step-by-step orchestration execution
- **archeflow:plan-phase** — Explorer + Creator behavior
- **archeflow:do-phase** — Maker implementation rules
- **archeflow:check-phase** — Reviewer protocols
- **archeflow:shadow-detection** — Recognizing and handling dysfunction
- **archeflow:custom-archetypes** — Creating domain-specific roles
- **archeflow:workflow-design** — Designing custom PDCA workflows
- **archeflow:autonomous-mode** — Unattended overnight sessions with full visibility