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 instructions/benkipnis/virtual_engineer/agents-mdgit clone --depth 1 https://github.com/benkipnis/virtual_engineerWhat 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 | $0.00493 | $0.00493 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
virtual_engineer AGENTS.md 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — Virtual Engineer
This repository is a runnable Virtual Engineer demo: MCP retrieval server, LLM agent, React UI, and Atlas sample data. It is not a generic toolkit.
Repository layout
| Path | Purpose |
|---|---|
backend/src/ |
Express server — MCP tools, LLM agent, SSE chat API |
backend/src/mcp/createServer.js |
20 MCP tool definitions |
backend/src/agent/ |
LLM orchestrator + MCP HTTP client |
backend/src/repositories/ |
MongoDB data access layer |
frontend/src/ |
Demo UI — Overview, Evidence Board, Field Chat |
scripts/data/ |
Sample data, schemas, seed scripts |
tests/connectivity/ |
MCP smoke tests |
docs/ |
Architecture, runbook, gates, phase status |
Local Cursor configuration
.cursor/ (rules and skills) is gitignored and kept locally for agent-assisted development. It is not part of the published repository.
Key workflows
Run and test
npm run mcp:dev # backend on :3100
npm run test:connectivity # requires server running
cd frontend && npm run dev # UI on :5173
Data changes
Edit scripts/data/samples/, then npm run seed:drop. See scripts/data/README.md.
Add or change MCP tools
- Implement repository function in
backend/src/repositories/ - Register tool in
backend/src/mcp/createServer.jswithquery_insightmetadata - Extend smoke tests in
tests/connectivity/
UI changes
Follow single-page multi-tab layout in frontend/src/. Both demo tabs share ChatContext SSE events.
Design principles
- Deterministic first — resolve asset and operational facts before knowledge/case search
- Real LLM agent — no scripted tool sequences in demo paths
- Transparency — surface
query_insight(pattern, collection, pipeline) in the UI - No customer branding — use generic OEM terminology in sample data and docs
Compliance artifacts
Maintain docs/gates.md and docs/phase-status.md when closing build phases.
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 · 56 lines · 493 tokens per session scan A 36096f2158d5
virtual_engineer AGENTS.md is an instructions file published in the GitHub repository benkipnis/virtual_engineer (1 stars, last pushed 5d ago), licensed MIT. It adds 493 tokens to every session, about $0.0025 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 instructions, from other repositories
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
nimbalyst AGENTS.md
AGENTS.md instructions for nimbalyst/nimbalyst: At the beginning of every AI session, read the root CLAUDE.md and any applicable package-level CLAUDE.md before taking actions.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
GENesis-AGI AGENTS.md
AGENTS.md instructions for WingedGuardian/GENesis-AGI, covering agent instructions, code review mandate (adversarial), gitnexus — code intelligence (advisory), genesis capability surface and skills.