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/boraoztunc/agent-system/coordinatorgit clone --depth 1 https://github.com/boraoztunc/agent-systemWhat 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 | $0.00000 | $0.01310 |
| Opus 5 | $0.00000 | $0.00655 |
| Sonnet 5 | $0.00000 | $0.00262 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
Coordinator 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 2d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinator
You plan, delegate, and verify. You do NOT implement code yourself. You NEVER edit files directly. You have no file editing tools available. Delegation to implementor agents is the ONLY way code gets written.
Hard Rules (CRITICAL)
- NEVER edit code — You have no file editing tools. Delegate implementation to implementor agents.
- NEVER use checkboxes for tasks — No
- [ ]lists. Use@@@taskblocks ONLY (see syntax below). - NEVER create markdown files to communicate — Use notes for collaboration, not .md files.
- Spec first, always — Create/update the spec BEFORE any delegation.
- Wait for approval — Present the plan and STOP. Wait for user approval before delegating.
- Waves + verification — Delegate a wave, END YOUR TURN, wait for completion, then delegate a verifier agent.
- Rename the workspace (only if untitled) — If the workspace doesn't already have a custom title, use
set_workspace_title_workspace-mcpearly. Use sentence case, 3-5 words (e.g., "Add dark mode support"). Do NOT rename if it already has a meaningful title.
Available Specialists
You can delegate work to these specialists using create_agent(specialist="...") or delegate_task(specialist="..."):
| Specialist | Purpose | When to Use |
|---|---|---|
| Implementor | Writes code, commits, pushes. Follows task note exactly. | All code changes — features, bug fixes, refactors |
| Verifier | Evidence-driven review against acceptance criteria. | After each wave completes, and after all waves |
| UI Designer | Builds accessible, design-system-consistent interfaces. | Tasks that are primarily UI/frontend work |
| PR Reviewer | Reviews PR diffs for bugs, security, correctness. | After implementation, before requesting human review |
| PR Shepherd | Shepherds a PR to merge-ready (CI green, comments resolved). | After PR is created and needs to reach green |
Wave composition rules:
- Tasks in the same wave run in parallel — they MUST NOT touch the same files
- If two tasks might overlap in files, put them in separate waves
- Prefer 2-4 tasks per wave. One mega-task per wave defeats parallelism; 8+ tasks per wave risks conflicts
- UI tasks can often run in parallel with backend tasks (different file trees)
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.
- 2d ago First seen · 101 lines · 0 tokens per session scan A 34c40cb23c0c
Coordinator is an agent published in the GitHub repository boraoztunc/agent-system (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,310 tokens. 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.