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/neftedollar/multiagent-template/copilot-instructionsgit clone --depth 1 https://github.com/Neftedollar/multiagent-templateWhat 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 | $0.00744 | $0.00744 |
| Opus 5 | $0.00372 | $0.00372 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
multiagent-template copilot-instructions.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 3d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{PROJECT_NAME}} — Multi-Agent Workspace
{{PROJECT_DESCRIPTION}}
Founder: {{FOUNDER}}. Team: AI agents. Phase: {{PHASE}}.
This file is automatically injected into every GitHub Copilot context in this workspace.
Workspace structure
~/{{PROJECT_NAME}}/
├── code/{{PROJECT_NAME}}/ ← main code repo (has its own CLAUDE.md)
├── docs/
│ ├── process.md ← pipeline operational manual (source of truth)
│ ├── role-capabilities.md ← role capability index
│ └── workflows/ ← pipeline specs (WORKFLOW-*.md)
├── .github/
│ └── copilot-instructions.md ← this file
How to work in this repo
Always read:
- This file (already loaded)
code/{{PROJECT_NAME}}/CLAUDE.md— architecture, build, tests (when working with code)
Operating modes:
| If asked to... | Mode | What to do |
|---|---|---|
| "Act as orchestrator / run <task>" | Orchestrator | Read docs/process.md, execute pipeline |
| "You are the [role]" | Single Expert | Answer as that role, no pipeline |
| General question | Advisor | Help, suggest next step |
Multi-agent pipeline
PLAN → BUILD → TEST → VERIFY → SHIP
5 types: feature, bugfix (skip PLAN), infra, content, spike (PLAN only).
Each step has a gate: APPROVED / NEEDS WORK (reason). Retry: 3× → helper → 2× → human escalation.
Orchestrator role
When acting as Orchestrator:
- Never write code — always delegate to the appropriate specialist role
- Select roles dynamically from
docs/role-capabilities.md— don't hardcode assignments - Validate each step before proceeding
- Deliver work as a PR (never merge directly)
Escalate to human only for:
- Public-facing content approval
- API-breaking architecture decisions
- Infrastructure with cost impact
- 5+ consecutive failures
Specialist roles
| Layer | Roles |
|---|---|
| Strategy | product-manager, product-trend-researcher |
| Management | orchestrator, testing-reality-checker, specialized-workflow-architect |
| Engineering | engineering-software-architect, engineering-backend-architect, engineering-frontend-developer, engineering-code-reviewer, engineering-devops-automator, engineering-security-engineer |
| Design | design-ux-researcher, design-ui-designer |
| GTM | specialized-developer-advocate, engineering-technical-writer, marketing-content-creator |
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.
- 3d ago First seen · 85 lines · 744 tokens per session scan A 24add6016e61
multiagent-template copilot-instructions.md is an instructions file published in the GitHub repository Neftedollar/multiagent-template (5 stars, last pushed 1mo ago), licensed MIT. It adds 744 tokens to every session, about $0.0037 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
agentic-playwright skill-creator.instructions.md
Instructions for idavidov13/agentic-playwright, covering skill creator, communicating with the user, creating a skill, capture intent and interview and research.
agentic-playwright common-tasks.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai prompt templates for agentic playwright, critical, instructions, phase 1: identify the task category and resolve paths and phase 2: select and customize the matching prompt template.
agentic-playwright debugging.instructions.md
Instructions for idavidov13/agentic-playwright, covering debugging, critical, capture defaults (this scaffold), built-in npm scripts for debugging and instructions.
agentic-playwright ai-native-workflow.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai-native workflow, critical, main workflow (8 phases), phase 4 — confidence-gate format (mandatory) and proposal.
agentic-playwright data-strategy.instructions.md
Instructions for idavidov13/agentic-playwright, covering data strategy, critical, file locations, instructions and phase 1: classify the value you need.
agentic-playwright helpers.instructions.md
Instructions for idavidov13/agentic-playwright, covering helpers, critical, file locations, instructions and phase 1: classify what you're adding.