Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/julianromli/droid-factory-template/orchestratorgit clone --depth 1 https://github.com/julianromli/droid-factory-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/julianromli/droid-factory-template/orchestrator)<a href="https://agentmods.dev/commands/julianromli/droid-factory-template/orchestrator"><img src="https://agentmods.dev/badge/commands/julianromli/droid-factory-template/orchestrator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.00531 |
| Opus 5 | $0.00005 | $0.00266 |
| Sonnet 5 | $0.00002 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator: Intelligent Project Execution
Execute the objective: $ARGUMENTS
Execution Flow
Phase 1: Discovery
Analyze the current project context organically:
- Check common files:
README.md,package.json,requirements.txt,plan.md,docs/,src/ - Detect tech stack from configuration files
- Use targeted file reading, avoid unnecessary directory listing
Phase 2: Planning
Create a phased execution approach:
- Load orchestrator patterns from
/orchestrator/ - Identify available specialist droids from
/droids/ - Create TodoWrite with comprehensive phase breakdown
- Determine optimal execution strategy based on dependency graph
Phase 3: Droid Selection
Auto-rank droids based on:
- Project complexity
- Tech stack match
- Dependency analysis
- Expertise level
Available Droid Categories:
- Backend: backend-architect, backend-security-coder, database-architect, database-optimizer
- Frontend: frontend-developer, nextjs-app-router-developer, ui-ux-designer
- Mobile: mobile-developer, flutter-expert
- Security: security-auditor, incident-responder
- Testing: test-automator, tdd-orchestrator, code-reviewer, debugger
- DevOps: devops-specialist, cloud-architect, kubernetes-architect
- Data: data-engineer, data-analyst, mlops-engineer
- Documentation: docs-architect, api-documenter, tutorial-engineer
Phase 4: Parallel Execution
Request Factory to execute specialist droids in parallel:
- Generate detailed prompts for each specialist
- Delegate to Factory for parallel droid execution
- Monitor progress and detect bottlenecks
Phase 5: Integration & Verification
- Synthesize results from all droids
- Ensure all components work together
- Run quality gates and verification checks
Key Principles
- Context-aware discovery - Find project structure organically
- Proactive issue resolution - Predict and prevent problems
- Adaptive execution - Adjust strategy based on complexity
- Continuous learning - Track success patterns and learn from failures
- Autonomous completion - Continue until project is fully complete
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 67 lines · 9 tokens per session scan A deb925873425
orchestrator is a command published in the GitHub repository julianromli/droid-factory-template (52 stars, last pushed 9mo ago), licensed MIT. It adds 9 tokens to every session and 531 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.