ironcurtain copilot-instructions.md

ironcurtain copilot-instructions.md is an instructions file for GitHub Copilot from provos/ironcurtain. It costs 850 tokens per session, scanned A, original, Apache-2.0.

Review rules for IronCurtain, a security runtime that checks every AI-agent tool call against policy before sending it to an MCP server. MCP servers are services that provide tools an agent can call.

In plain words
What is it for?
Use it when reviewing policy-engine changes, MCP forwarding, trusted-server exceptions, platform support, or code that handles tool-call security.
Why use it?
It helps reviewers catch security bypasses, platform mistakes, and incorrect handling of trusted servers at the boundary where agent requests are approved.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

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/provos/ironcurtain/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/provos/ironcurtain

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 ironcurtain copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/provos/ironcurtain/copilot-instructions.svg)](https://agentmods.dev/instructions/provos/ironcurtain/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/provos/ironcurtain/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/provos/ironcurtain/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 850 This file is loaded in full into every session.
When invoked 850 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 5.1 $0.00850 $0.00850
Opus 5 $0.00425 $0.00425
Sonnet 5 $0.00170 $0.00170
Haiku 4.5 $0.00085 $0.00085

Measured 6d ago against content hash 717b57c86929, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ironcurtain 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 6d 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IronCurtain Copilot Review Instructions

IronCurtain is a secure agent runtime that mediates between an AI agent and MCP servers. Every tool call passes through a trusted process that evaluates it against policy rules before forwarding. The policy engine and MCP proxy are the security boundary.

Platform Support

IronCurtain runs on macOS and Linux. Windows is only supported under WSL2 — native Windows is not a target platform.

Security Invariants

  • Every tool call MUST pass through policyEngine.evaluate() before forwarding to a real MCP server. Any code path that skips evaluation is a security bypass.
  • Trusted servers are an intentional exception to annotation requirements. Servers in the trustedServers set (currently only the memory MCP server) bypass structural invariants and compiled rules via an early return in evaluate(). This is by design: trusted server tools have no filesystem paths or URLs, so structural invariants (protected paths, sandbox containment, domain gate) are not applicable and would require fake annotations. Trust is verified by matching both the server name AND the expected entrypoint path (MEMORY_SERVER_ENTRY), not name alone. The normal flow (annotation lookup → evaluate → forward → audit) still runs; only prepareToolArgs is skipped when no annotation exists.
  • Path containment checks MUST use resolveRealPath() (symlink resolution) before comparison. Raw path.resolve() is a symlink-escape vulnerability.
  • isWithinDirectory() appends a trailing / before startsWith(). Without it, /tmp/sandbox-evil matches /tmp/sandbox.
  • Multi-role evaluation uses most-restrictive-wins (deny > escalate > allow). Least-restrictive is a privilege escalation.
  • Unknown tools (without annotations) MUST be denied, unless the server is in the trustedServers set.
  • The auto-approver can only return approve or escalate, never deny. Error paths must return escalate (fail-open to human).
  • SERVER_CREDENTIALS must be deleted from process.env immediately after parsing to prevent child process leakage.
  • Audit logging must occur for every tool call outcome. No code path should skip it.

Read the full file on GitHub · 48 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. 6d ago First seen · 48 lines · 850 tokens per session scan A 717b57c86929

Subscribe to this mod's changes

ironcurtain copilot-instructions.md is an instructions file published in the GitHub repository provos/ironcurtain (600 stars, last pushed yesterday), licensed Apache-2.0. It adds 850 tokens to every session, about $0.0042 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.

Related

Other instructions, from other repositories

agentos CLAUDE.md

Claude Code instructions for rivet-dev/agentos, covering agentos, boundaries, security model, sqlite schema ownership and runtime and registry.

rivet-dev/agentos · 4,057 tokens

agent-sandbox AGENTS.md

AGENTS.md instructions for kubernetes-sigs/agent-sandbox, covering agents.md, project summary, repository layout, agent skills and build, test, lint.

kubernetes-sigs/agent-sandbox · 4,327 tokens

agent-sandbox copilot-instructions.md

Copilot instructions for kubernetes-sigs/agent-sandbox: Project Context & Architecture: Refer to AGENTS.md for full project background, module layout, toolchain versions, and core conventions.

kubernetes-sigs/agent-sandbox · 293 tokens

mcp-server-starrocks CLAUDE.md

Claude Code instructions for StarRocks/mcp-server-starrocks, covering claude.md, project overview, development commands, run the server directly for testing and run with test mode to verify table overview functionality.

StarRocks/mcp-server-starrocks · 907 tokens

after-effects-mcp AGENTS.md

AGENTS.md instructions for JUNKDOGE-JOE/after-effects-mcp, covering repository development and delivery rules, 0.0 read the current architecture direction first, 0. user authorization is the scope boundary, 1. measure outcomes, not activity and 2. prioritize by dependency and user value.

JUNKDOGE-JOE/after-effects-mcp · 6,738 tokens

Symbiont AGENTS.md

AGENTS.md instructions for ThirdKeyAI/Symbiont, covering symbiont — agent instructions, project structure, build and test, code style and commit guidelines.

ThirdKeyAI/Symbiont · 4,251 tokens