a2a-demos copilot-instructions.md

a2a-demos copilot-instructions.md is an instructions file for GitHub Copilot from capiscio/a2a-demos. It costs 901 tokens per session, scanned A, original, MIT.

Repository-specific instructions for a2a-demos, a collection of developer demonstrations of agent security using different AI frameworks. They require work to go through pull requests and prohibit unbounded watch or blocking commands.

In plain words
What is it for?
They guide work on the demo agents, including reading the project’s sprint and session files, creating changes through pull requests, and avoiding indefinite-running commands.
Why use it?
They make the project’s contribution rules and working context clear before changes are made, reducing the risk of direct changes to the main branch or commands that never finish.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/capiscio/a2a-demos/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/capiscio/a2a-demos

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for a2a-demos copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/capiscio/a2a-demos/copilot-instructions.svg)](https://agentmods.dev/instructions/capiscio/a2a-demos/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/capiscio/a2a-demos/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/capiscio/a2a-demos/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 901 This file is loaded in full into every session.
When invoked 901 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00901 $0.00901
Opus 5 $0.00451 $0.00451
Sonnet 5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 3d ago against content hash be5ebaf43d40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

a2a-demos 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.

.github/copilot-instructions.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

a2a-demos - GitHub Copilot Instructions

⛔ ABSOLUTE RULES - NO EXCEPTIONS

1. ALL WORK VIA PULL REQUESTS

  • NEVER commit directly to main. All changes MUST go through PRs.

2. NO WATCH/BLOCKING COMMANDS

  • NEVER run blocking commands without timeout
  • Agent servers must have explicit shutdown mechanisms

🚨 CRITICAL: Read First

Before starting work, read the workspace context files:

  1. ../../.context/CURRENT_SPRINT.md
  2. ../../.context/ACTIVE_TASKS.md
  3. ../../.context/SESSION_LOG.md

Repository Purpose

a2a-demos contains interactive demo agents showcasing CapiscIO security with different AI frameworks. These are NOT production code — they're developer-facing demos for documentation, conference talks, and onboarding.

Architecture

a2a-demos/
├── enforcement-demo/        # Enforcement demo (Zero to Enforcement)
├── policy-demo/             # Policy as Code demo
├── multi-agent-demo/        # Multi-framework agent trust demo
│   ├── agents/
│   │   ├── langchain-agent/ # LangChain research agent
│   │   ├── crewai-agent/    # CrewAI multi-agent crew
│   │   └── langgraph-agent/ # LangGraph stateful agent
│   ├── shared/              # Shared CapiscIO integration code
│   ├── run_demo.py          # Automated demo script
│   ├── run-agents.sh        # Start all agents
│   ├── setup.sh             # Install all agent venvs
│   └── .env.example         # Agent credentials template
└── .env                     # Agent credentials (gitignored)

Key Patterns

CapiscIO SDK Integration

Each agent uses the Python SDK to register identity and emit events:

from capiscio_sdk import CapiscIO

# Let's Encrypt-style setup (v2.4.1+)
capiscio = await CapiscIO.connect(
    agent_id="<uuid>",
    api_key="sk_live_...",
    server_url="https://registry.capisc.io"
)

# Emit events during agent execution
await capiscio.emit("task_started", {"query": "..."})

Each Agent Has Its Own venv

cd multi-agent-demo/agents/langchain-agent
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Read the full file on GitHub · 130 lines

Changes

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.

  1. 3d ago First seen · 130 lines · 901 tokens per session scan A be5ebaf43d40

Subscribe to this mod's changes

a2a-demos copilot-instructions.md is an instructions file published in the GitHub repository capiscio/a2a-demos (23 stars, last pushed 3mo ago), licensed MIT. It adds 901 tokens to every session, about $0.0045 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 2026-08-30.