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/comma-compliance/arc-relay/copilot-instructionsgit clone --depth 1 https://github.com/comma-compliance/arc-relayWrote 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/comma-compliance/arc-relay/copilot-instructions)<a href="https://agentmods.dev/instructions/comma-compliance/arc-relay/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/comma-compliance/arc-relay/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 | $0.00367 | $0.00367 |
| Opus 5 | $0.00183 | $0.00183 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
arc-relay 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 5d 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.
What it actually says
Arc Relay - AI Assistant Context
Arc Relay is an open-source MCP (Model Context Protocol) control plane written in Go. It provides auth, policy controls, traffic interception, and archiving for AI tool calls.
Project Structure
cmd/arc-relay/- Server binary (CGO required for SQLite)cmd/arc-sync/- CLI tool for syncing MCP servers to projects (pure Go)internal/middleware/- Bidirectional middleware pipeline (archive, sanitizer, sizer, alerter)internal/proxy/- MCP proxy backends (stdio bridge, HTTP, remote with OAuth)internal/store/- SQLite persistence layer with migrationsinternal/web/- HTTP handlers and server-rendered HTML templatesinternal/config/- TOML config + ARC_RELAY_* env var overridesinternal/cli/- CLI packages (config, sync, project detection)
Building
CGO_ENABLED=1 go build ./cmd/arc-relay # Server (needs gcc, libsqlite3-dev)
CGO_ENABLED=0 go build ./cmd/arc-sync # CLI (pure Go, cross-platform)
go test ./... # Run all tests
go vet ./... # Static analysis
Key Patterns
- Middleware implements
ProcessRequestandProcessResponseonmcp.Request/mcp.Response - Request middleware runs in order; response middleware runs in reverse order
- Config: TOML file + env var overrides (ARC_RELAY_, ARC_SYNC_)
- Auth: session cookies (web UI) + Bearer API keys (proxy)
- Archive dispatcher uses SQLite queue with retry backoff and circuit breaker
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.
- 5d ago First seen · 32 lines · 367 tokens per session scan A 0f37debd4a50
arc-relay copilot-instructions.md is an instructions file published in the GitHub repository comma-compliance/arc-relay (57 stars, last pushed 5d ago), licensed MIT. It adds 367 tokens to every session, about $0.0018 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
agent CLAUDE.md
Claude Code instructions for 1mcp-app/agent, covering claude.md, repository information, development commands, setup and build & run.
one-mcp AGENTS.md
Instructions for burugo/one-mcp, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
muster CLAUDE.md
Claude Code instructions for giantswarm/muster, covering claude.md, what is muster, build & development commands, build and install and testing.
preloop AGENTS.md
AGENTS.md instructions for preloop/preloop, covering preloop development guide, commands, git workflow, keep sample data generic and code style.
helio AGENTS.md
AGENTS.md instructions for gethelio/helio, covering helio, architecture, monorepo structure, tech stack and commands.
MCPbundler AGENTS.md
Instructions for eugenepyvovarov/MCPbundler, covering repository guidelines, project structure & module organization, documentation (obsidian), build, test, and development commands and headless stdio environment flags.