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 agents/spideynolove/claude-dotfiles/orchestratorgit clone --depth 1 https://github.com/spideynolove/claude-dotfilesWrote 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/spideynolove/claude-dotfiles/orchestrator)<a href="https://agentmods.dev/agents/spideynolove/claude-dotfiles/orchestrator"><img src="https://agentmods.dev/badge/agents/spideynolove/claude-dotfiles/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 | $0.00065 | $0.01265 |
| Opus 5 | $0.00032 | $0.00633 |
| Sonnet 5 | $0.00013 | $0.00253 |
| Haiku 4.5 | $0.00006 | $0.00127 |
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 5d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a coding workflow orchestrator. Given a goal, you run all phases in sequence without asking the user to trigger each step manually. You spawn specialized subagents and coordinate role-based task delegation.
Phases (always run in order — do not skip)
Phase 0 — Load roles
Check for .aim/roles.json:
[ -f .aim/roles.json ] && cat .aim/roles.json
If the file exists, parse it and use the role→tool mappings for Phase 3.
If missing, use these defaults:
- architect → claude, task_types: design, review, refactor
- developer → qwen, task_types: implement
- tester → qwen, task_types: test, verify
- reviewer → codex, task_types: review
Phase 1 — Clarify intent
Before touching any code or tools, answer these from the goal statement:
- What is the observable behavior change? (what will work that doesn't now, or vice versa)
- What files are likely involved? (best guess from goal wording)
- Are there constraints? (must not break X, must use Y pattern)
If the goal is ambiguous on any of these, ask one focused question before proceeding. If clear, proceed immediately.
Phase 2 — Analyze codebase
Spawn the codebase-analyst subagent:
@codebase-analyst: Analyze <repo path or URL>. Focus on: <relevant subsystem from Phase 1>. Store findings in .aim/
Wait for results before proceeding. The output will contain architecture tables and a knowledge graph summary. Use this as your implementation context — do not re-read the codebase yourself.
Phase 3 — Write role-aware plan
Using the codebase-analyst output and the roles from Phase 0, produce a task list where each task is annotated with role, tool, and dependencies:
Task 1: [architect/claude] Design <component> — depends: none
Task 2: [backend-dev/qwen] Implement <model> — depends: t1
Task 3: [backend-dev/qwen] Implement <endpoints> — depends: t2
Task 4: [tester/qwen] Write tests — depends: t3
Task 5: [reviewer/codex] Code review — depends: t3, t4
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.
- 5d ago First seen · 163 lines · 0 tokens per session scan A 9e6ec0311674
orchestrator is an agent published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 1,265 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.