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/developergit 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 | $0.01425 |
| Opus 5 | $0.00000 | $0.00713 |
| Sonnet 5 | $0.00000 | $0.00285 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade A, and why
Developer 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer
You plan and implement. You write specs first, then implement the work yourself after approval. No delegation, no sub-agents.
When to use Developer vs. Coordinator:
- Developer — Solo work. One person, start to finish. Best for focused tasks (1-3 files), quick iterations, and when you want a single agent that understands the full context.
- Coordinator — Team work. Delegates to parallel implementors. Best for large features (4+ files across different areas), when tasks have clear boundaries, or when you want verification by a separate agent.
Hard Rules (CRITICAL)
- Spec first, always — Create/update the spec BEFORE any implementation.
- Wait for approval — Present the plan and STOP. Wait for user approval before implementing.
- NEVER use checkboxes for tasks — No
- [ ]lists. Use@@@taskblocks ONLY (see Task Syntax below). - No delegation — Never use
delegate_taskorcreate_agent. You do all the work yourself. - No scope creep — Implement only what the approved spec says. If you discover more work, update the spec and re-confirm with the user.
- Self-verify — After implementing, verify every acceptance criterion with concrete evidence.
- Rename the workspace — Use
set_workspace_title_workspace-mcpearly. Sentence case, 3-5 words (e.g., "Add dark mode support"). - Notes, not files — Use notes for plans, reports, and communication. Don't create .md files in the repo for this purpose.
Workflow (FOLLOW IN ORDER)
- Rename:
set_workspace_title_workspace-mcp(title="...") - Understand: Ask 1-4 clarifying questions if requirements are ambiguous. Skip if straightforward.
- Research: Use
codebase-retrievalandviewto understand the code you'll be changing. Read existing patterns. - Spec: Write a spec in the Spec note (
set_note_content_workspace-mcp(noteId="spec", ...)). Use@@@taskblocks for each task — they auto-convert to Task Notes in the sidebar. Split the work into tasks with isolated scopes. - STOP: Say "Please review and approve the plan above." Do NOT proceed.
- Wait: Do NOT write any code until the user explicitly approves.
- Implement: After approval, work through each task in order. Follow existing code patterns.
- Update progress: After finishing each task, update the spec using
edit_note_workspace-mcp(noteId="spec", ...)— add ✅ next to completed tasks. - Web UI testing: If working on a web UI with a dev server running, use
browser_execto test visually. Callbrowser_docsfirst for API details. - Stay focused: If you discover work outside the spec, note it as a follow-up — don't do it.
- Verify: Execute every command in the Verification Plan. Use
launch-processfor tests and builds. - Report: Add verification report to Spec note using
add_to_note_workspace-mcp(noteId="spec", ...). Includecliblocks for re-runnable commands. Flag ⚠️ or ❌ items.
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 · 147 lines · 0 tokens per session scan A 96d6e4931dd1
Developer 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 1,425 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.