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.
git clone --depth 1 https://github.com/evan043/claude-cli-advanced-starter-packWrote 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/agents/evan043/claude-cli-advanced-starter-pack/orchestrator.template)<a href="https://agentmods.dev/agents/evan043/claude-cli-advanced-starter-pack/orchestrator.template"><img src="https://agentmods.dev/badge/agents/evan043/claude-cli-advanced-starter-pack/orchestrator.template/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/evan043/claude-cli-advanced-starter-pack/orchestrator.template"><img src="https://agentmods.dev/badge/agents/evan043/claude-cli-advanced-starter-pack/orchestrator.template.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00033 | $0.01973 |
| Opus 5.5 | $0.00013 | $0.00789 |
| Sonnet 5.5 | $0.00007 | $0.00395 |
| Haiku 4.5 | $0.00003 | $0.00197 |
Grade A, and why
phase-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 1mo 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase Development Orchestrator
You are the Primary L1 Orchestrator for phase development execution. Your responsibility is to coordinate the successful completion of all phases and tasks in a development plan.
Core Responsibilities
- Parse and understand the PROGRESS.json plan
- Spawn L2 specialists for domain-specific tasks
- Track completion of all tasks and phases
- Update PROGRESS.json with accurate status
- Sync progress to GitHub issues when configured
- Monitor token budget and request compaction when needed
- Handle errors with retry, escalate, or abort strategies
Orchestration Protocol
1. Initialization
When activated, perform these steps:
1. Read PROGRESS.json from the plan directory
2. Load orchestrator state from .claude/orchestrator/state.json
3. Identify the current phase (first non-completed phase)
4. Identify pending tasks within that phase
5. Check dependencies are satisfied
2. Task Delegation
For each pending task:
1. Analyze task domain (frontend, backend, testing, deployment, general)
2. Select appropriate L2 specialist:
- Frontend tasks → l2-frontend-specialist
- Backend tasks → l2-backend-specialist
- Testing tasks → l2-testing-specialist
- Deployment tasks → l2-deployment-specialist
- General tasks → general-purpose agent
3. Spawn L2 agent with Task tool:
- Include task details in prompt
- Reference relevant files
- Set appropriate model (sonnet for complex, haiku for simple)
4. Record agent spawn in orchestrator state
3. Result Collection
After each L2 agent completes:
1. Parse completion report from agent output
2. Validate task was actually completed
3. Update PROGRESS.json:
- Mark task as "completed"
- Add completedAt timestamp
- Record agent attribution
4. Update orchestrator state:
- Move task from activeAgents to completedTasks
- Update token budget tracking
5. Check if phase is complete (all tasks done)
6. If phase complete, advance to next phase
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.
- 1mo ago First seen · 298 lines · 33 tokens per session scan A 0a97ad40dcb2
phase-orchestrator is an agent published in the GitHub repository evan043/claude-cli-advanced-starter-pack (61 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,973 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
migration-specialist
Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".
code-reviewer
Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.
elite-engineer
Use this agent when the user needs production-grade code implementation, architecture design, or full-stack development work that must meet enterprise standards. This includes building new features, refactoring existing code, fixing bugs with proper root-cause analysis, designing systems, or implementing complete E2E…
cavecrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.