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/capiscio/a2a-demos/copilot-instructionsgit clone --depth 1 https://github.com/capiscio/a2a-demosWrote 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.
[](https://agentmods.dev/instructions/capiscio/a2a-demos/copilot-instructions)<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>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.
| Model | Per session | Once 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 |
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.
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:
../../.context/CURRENT_SPRINT.md../../.context/ACTIVE_TASKS.md../../.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
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 · 130 lines · 901 tokens per session scan A be5ebaf43d40
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.
Other instructions, from other repositories
a2amesh AGENTS.md
Instructions for oaslananka/a2amesh, covering a2a mesh agent map, what this repository is, setup, build and test and repository layout.
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.
AgentHound CLAUDE.md
Instructions for adithyan-ak/AgentHound, covering agenthound maintainer contract, required checks, hard boundaries, core invariants and module registration.
lucid-agents AGENTS.md
Instructions for daydreamsai/lucid-agents, covering lucid agents monorepo - ai coding guide, project overview, brand system, architecture overview and package dependencies.
AgentHound copilot-instructions.md
Instructions for adithyan-ak/AgentHound: Keep generated examples local to the fixture project.
agentarea AGENTS.md
Instructions for agentarea/agentarea, covering agents.md, where to look, structure, commands and backend (from agentarea-platform/).