← Back to Skills Marketplace
genortg

Genor's Project Orchestration

by Krzysztof · GitHub ↗ · v2.2.1 · MIT-0
cross-platform ⚠ suspicious
37
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install genor-orchestrator
Description
Unified orchestration: model routing, coding workflow, planning, verification, and project management
README (SKILL.md)

Genor's Project Orchestration

Single source of truth for agentic development work, model orchestration, and project management.

Core Principles

  1. Codebase First — Never touch code without understanding it first
  2. Plan Before Actupdate_plan for anything beyond one edit
  3. Verify Before Claim — No completion claim without fresh evidence
  4. Self-Review — Every output gets audited before delivery
  5. Fail Gracefully — Every step has a fallback chain
  6. Document Everything — Log sessions, decisions, architecture

Data Directory

All user data lives in orchestrator-data/ (set ORCHESTRATOR_DATA_DIR to override).

orchestrator-data/
├── models.json          — model inventory
├── session_log.md       — session history table
├── price_changes.log    — price tracking
├── MODEL_CATALOG.md     — generated catalog
├── projects/            — per-project session tracking
│   └── \x3Cname>/sessions.json
└── sessions/            — detailed session state files
    └── YYYY-MM-DD-HHMM-\x3Cproject>-\x3Ctask-slug>.md

Scripts

Script Purpose
bash {baseDir}/scripts/onboard.sh First-time setup
bash {baseDir}/scripts/init-project.sh \x3Cpath> \x3Cname> [stack] Scaffold project
bash {baseDir}/scripts/log-session.sh ... Log session
bash {baseDir}/scripts/log-decision.sh ... Log ADR
bash {baseDir}/scripts/check-prices.sh Price check
bash {baseDir}/scripts/discover-models.sh Probe providers
bash {baseDir}/scripts/test-model.sh \x3Cid> Test connectivity
bash {baseDir}/dashboard/serve.sh Start dashboard

Conversational Triggers

  • "onboard" → bash scripts/onboard.sh
  • "start dashboard" → bash dashboard/serve.sh
  • "onboard project X" → bash scripts/init-project.sh \x3Cpath> \x3Cname>
  • "check prices" → bash scripts/check-prices.sh

Execution Workflow

Phase 0: Init

Understand the codebase (exec find . -name '*.ts' | head -50), search memory, research.

Phase 1: Plan

Call update_plan. Size the work: small (1-3 files), medium (3-8), large (8+ → decompose).

Phase 2: Execute

Scenario Primary Fallback
Single-line edit edit tool exec sed
Multi-file change ACP coding agent Manual edit
Research Sub-agent Web search
Debugging Phase 5 protocol Mental trace
Testing Test framework Manual
Browser testing Browser tool curl

Phase 3: Verify

Build → Test → Lint → Screenshot (if UI). No claim without evidence.

Phase 4: Manage

Update .planning/STATE.md and .planning/ROADMAP.md after every session.

Phase 5: Diagnose

Reproduce → Hypothesise (3-5 causes) → Instrument one variable → Fix → Regression test.

Phase 6: Tool Fallbacks

Tool Fallback chain
Codebase discovery exec findexec ls -R → read key files
update_plan mental plan → STATE.md note
ACP coding agent CLI variant → sub-agent → manual edit
edit tool exec sedwrite full file
Build tsc --noEmitnode --check
Test specific test file → manual
Vision cloud → local → describe
Memory search lcm_grepexec grep

Model Routing

Task Type Primary Fallback 1 Fallback 2
Heavy coding Best available ACP agent Fast cloud
Quick edits Fast cloud Free tier Local
Research Best reasoning Free tier Local
Vision Cloud vision Local Describe
Planning / design Best reasoning Free tier Fast cloud
Docs / summaries Free tier Fast cloud Local

See {baseDir}/ROUTING.md for the current routing table. See orchestrator-data/MODEL_CATALOG.md for full inventory.

Sub-Agent Protocol

Every spawned sub-agent MUST include:

IMPORTANT: Follow orchestration conventions:
- Understand the codebase first (exec find as fallback)
- Plan before coding (update_plan or mental plan)
- Verify before claiming (build, test, screenshot)
- Self-review output before returning
- Use fallback chains when tools are unavailable

Design Grilling

Before significant architectural work, conduct a structured interview:

  1. One question at a time, wait for feedback
  2. Challenge terms that conflict with existing CONTEXT.md
  3. Propose precise canonical terms for vague language
  4. Stress-test with edge cases
  5. Cross-reference with code; surface contradictions

Generate: CONTEXT.md (glossary), .planning/ADRs/ (decisions), summary.

ADR criteria (all three must be true): hard to reverse, surprising without context, real trade-off.

References

Resource Path
Full documentation {baseDir}/references/README.md
Onboarding guide {baseDir}/references/ONBOARDING.md
Execution reference {baseDir}/references/EXECUTION.md
Debugging guide {baseDir}/references/DEBUGGING.md
Fallback tables {baseDir}/references/FALLBACKS.md
Routing table {baseDir}/ROUTING.md
Model catalog orchestrator-data/MODEL_CATALOG.md
Dashboard http://localhost:8766 (when running)
Usage Guidance
Review before installing. Use it only if you are comfortable with local persistent orchestration logs and network provider probes. Keep the dashboard bound to localhost or behind a firewall, avoid logging secrets or proprietary context, and only enable cron or PM2 after explicitly deciding you want long-running persistence.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The scripts and dashboard match the stated orchestration purpose, but the dashboard can mutate model configuration and the onboarding flow encourages broad project discovery beyond user-specified paths.
Instruction Scope
The skill documents data directories and scripts, but uses a very broad conversational trigger and does not consistently require granular consent before network probes, project discovery, logging, dashboard startup, cron, or PM2 use.
Install Mechanism
Installation metadata requires only bash, curl, and python3, with no dependency install or automatic destructive setup found; sensitive actions are mostly in user-invoked scripts.
Credentials
The dashboard binds to 0.0.0.0, allows cross-origin requests, and exposes unauthenticated POST and DELETE endpoints for persistent model records, which is broader than a local admin tool should need by default.
Persistence & Privilege
The skill persistently writes session logs, detailed context files, project tracking JSON, optional ADRs, price logs, and can use PM2 or cron; these behaviors are purpose-aligned but under-scoped and lack redaction or retention controls.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install genor-orchestrator
  3. After installation, invoke the skill by name or use /genor-orchestrator
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.2.1
v2.2.1: No skill content changes — reverted accidental LCM rule addition to SKILL.md (LCM rules are agent-level, not skill-level). Skill remains self-contained with no external references.
v2.2.0
v2.2: Complete rewrite — lean SKILL.md (153 lines, was 362), split docs into references/, removed all external skill/personal data references, self-contained with only orchestrator-data/ as external dependency, fixed ecosystem.config.js paths, removed deleted skill references, fixed model status normalization
Metadata
Slug genor-orchestrator
Version 2.2.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Genor's Project Orchestration?

Unified orchestration: model routing, coding workflow, planning, verification, and project management. It is an AI Agent Skill for Claude Code / OpenClaw, with 37 downloads so far.

How do I install Genor's Project Orchestration?

Run "/install genor-orchestrator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Genor's Project Orchestration free?

Yes, Genor's Project Orchestration is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Genor's Project Orchestration support?

Genor's Project Orchestration is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Genor's Project Orchestration?

It is built and maintained by Krzysztof (@genortg); the current version is v2.2.1.

💬 Comments