ironcurtain types.instructions.md

A set of review rules for security-critical type definitions, which describe the allowed states, path roles, and contracts shared across the application.

In plain words
What is it for?
Use it when adding policy states or argument roles, changing path resolution, or reviewing which sandbox paths can bypass extra rule checks.
Why use it?
It prevents changes to these types from silently weakening policy decisions, path protection, or compile-time checks.

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

Made for: GitHub Copilot.

Per session 434 This file is loaded in full into every session.
When invoked 434 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 $0.00434 $0.00434
Opus 5 $0.00217 $0.00217
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00043 $0.00043

Measured 3d ago against content hash c5e7ed9aea85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ironcurtain types.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/instructions/types.instructions.md · 18 lines

What it actually says

Types Review Rules

Types in this directory define security-critical contracts shared across the codebase.

Mandatory Checks

  • PolicyDecisionStatus must remain a three-state union: allow | deny | escalate. Adding or removing states changes the security model.
  • ArgumentRole is a union type with a compile-time completeness check (_ROLE_COMPLETENESS_CHECK). Adding a new role requires updating: the union type, the registry map, the completeness check record, and any relevant tool annotations.
  • resolveRealPath() in argument-roles.ts is the canonical path resolution function. It must try realpathSync() first (symlink resolution), then parent-based resolution, then path.resolve() fallback. Simplifying the fallback chain removes symlink protection.
  • SANDBOX_SAFE_PATH_ROLES controls which path roles bypass compiled rule evaluation when all paths resolve inside the sandbox. The set includes read-path, write-path, delete-path, write-history, and delete-history. The history roles are safe here because they only discharge the path component — git operations that also carry a git-remote-url role (e.g., git_push) still require compiled rule evaluation for the URL role. Do not add non-path roles (like git-remote-url or github-repo) to this set.
  • SessionId uses a branded type pattern. Do not remove the __brand property or accept plain string where SessionId is expected.
  • RoleDefinition.serverNames controls which servers see a role in annotation prompts. Universal roles (no serverNames) appear for all servers. Accidental removal of serverNames would expose server-specific roles globally.
  • resolveStoredAnnotation() in argument-roles.ts is the sole boundary where conditional role specs are resolved into plain ArgumentRole[]. Conditional roles can only narrow from the default (subset invariant enforced by Zod). Do not add alternative resolution paths — all consumers must receive pre-resolved ToolAnnotation.
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 · 18 lines · 434 tokens per session scan A c5e7ed9aea85

Subscribe to this mod's changes

ironcurtain types.instructions.md is an instructions file published in the GitHub repository provos/ironcurtain (596 stars, last pushed 4d ago), licensed Apache-2.0. It adds 434 tokens to every session, about $0.0022 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

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

kubernetes-sigs/agent-sandbox · 4,218 tokens

agent-sandbox copilot-instructions.md

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

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

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

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

ThirdKeyAI/Symbiont · 4,039 tokens