Install
openclaw skills install genor-orchestratorUnified orchestration: model routing, coding workflow, planning, verification, and project management
openclaw skills install genor-orchestratorSingle source of truth for agentic development work, model orchestration, and project management.
update_plan for anything beyond one editAll 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
│ └── <name>/sessions.json
└── sessions/ — detailed session state files
└── YYYY-MM-DD-HHMM-<project>-<task-slug>.md
| Script | Purpose |
|---|---|
bash {baseDir}/scripts/onboard.sh | First-time setup |
bash {baseDir}/scripts/init-project.sh <path> <name> [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 <id> | Test connectivity |
bash {baseDir}/dashboard/serve.sh | Start dashboard |
bash scripts/onboard.shbash dashboard/serve.shbash scripts/init-project.sh <path> <name>bash scripts/check-prices.shUnderstand the codebase (exec find . -name '*.ts' | head -50), search memory, research.
Call update_plan. Size the work: small (1-3 files), medium (3-8), large (8+ → decompose).
| 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 |
Build → Test → Lint → Screenshot (if UI). No claim without evidence.
Update .planning/STATE.md and .planning/ROADMAP.md after every session.
Reproduce → Hypothesise (3-5 causes) → Instrument one variable → Fix → Regression test.
| Tool | Fallback chain |
|---|---|
| Codebase discovery | exec find → exec ls -R → read key files |
update_plan | mental plan → STATE.md note |
| ACP coding agent | CLI variant → sub-agent → manual edit |
edit tool | exec sed → write full file |
| Build | tsc --noEmit → node --check |
| Test | specific test file → manual |
| Vision | cloud → local → describe |
| Memory search | lcm_grep → exec grep |
| 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.
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
Before significant architectural work, conduct a structured interview:
Generate: CONTEXT.md (glossary), .planning/ADRs/ (decisions), summary.
ADR criteria (all three must be true): hard to reverse, surprising without context, real trade-off.
| 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) |