What is cyvisguard AGENTS.md?

A set of instructions for AI coding agents working in CyVisGuard, an open-source system that checks whether agents’ tool use matches a user’s intent. It explains the project structure, commands, and how tool calls are handled.

Use it to orient agents in a TypeScript pnpm monorepo, run tests and builds, start the dashboard, and understand the path of a tool call.

It gives an agent the context it needs before changing the code, reducing confusion about the repository and its security-control logic.

How flankerhqd/cyvisguard configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to flankerhqd/cyvisguard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/flankerhqd/cyvisguard/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/flankerhqd/cyvisguard

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/flankerhqd/cyvisguard/agents-md.svg)](https://agentmods.dev/instructions/flankerhqd/cyvisguard/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/flankerhqd/cyvisguard/agents-md"><img src="https://agentmods.dev/badge/instructions/flankerhqd/cyvisguard/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,164 This file is loaded in full into every session.

When invoked 2,164 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02164	$0.02164
Opus 5	$0.01082	$0.01082
Sonnet 5	$0.00433	$0.00433
Haiku 4.5	$0.00216	$0.00216

Measured 6d ago against content hash 952cf8ffb42a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

cyvisguard AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`Cannot find module './###.js'`. Fix: kill it, `rm -rf apps/dashboard/.next`,

AGENTS.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Orientation for AI agents working in this repo. Read this before editing. For a visual tour of the architecture, run the dashboard and open /docs.

What this is

CyVisGuard — an open-source, self-contained reference implementation of an enterprise AI-agent security control plane. It sits between agents and the tools they can touch, and on every tool call decides: who is calling, on behalf of whom, and is the behavior still within the user's intent?

It is not demo-ware: the control-plane logic is real and auditable. What's scripted vs. live is labeled honestly (see Honesty).

Stack: TypeScript pnpm monorepo, ESM, Node ≥ 20. Vitest for tests, tsx for scripts. Dashboard is Next.js 15 (App Router) + SSE.
Zero external runtime deps: no API keys, no DB, no network. Pure in-memory TS. The one optional exception is Ollama for S2 live mode (below).

Commands

pnpm install
pnpm test          # vitest, ~84 tests across the control plane
pnpm typecheck     # tsc --noEmit in every package
pnpm build         # tsc build of all packages
pnpm dev           # dashboard → http://localhost:4300
pnpm dev:headless  # run scenarios in the terminal (apps/headless)

Before you claim a change works, all three gates must be green: pnpm test, pnpm typecheck, and pnpm --filter @cyvisguard/dashboard build (the dashboard is not covered by the package build/typecheck).

Layout

packages/          the control plane (each package = one layer/concern)
apps/dashboard     live SOC dashboard (Next.js + SSE)
apps/headless      terminal scenario runner

package	role
`@cyvisguard/shared`	domain types, `EventBus`/`CyEvent`, and the 4 integration seams
`@cyvisguard/registry`	asset registration + config-fingerprint admission
`@cyvisguard/identity`	short-lived NHI identity, attestation, RFC-8693-style token exchange with nested `act` delegation chains, cascade revoke
`@cyvisguard/gateway`	PEP: policy enforcement + data-plane taint tagging + entity extraction
`@cyvisguard/policy`	pure-TS policy evaluator (integrity / task-scope / rate / data-flow / lethal-trifecta / step-up) + scope-extension arbitration
`@cyvisguard/intent`	natural-language task → structured `task_context`
`@cyvisguard/runtime-guard`	rule-based intent-alignment scoring + circuit breaker
`@cyvisguard/soc`	attack-chain reconstruction from the event stream
`@cyvisguard/agent-runtime`	`LLMProvider` + Ollama provider + a ReAct loop for live-injection mode
`@cyvisguard/scenario-engine`	scenario runners `runMs1`/`runS2`/`runS2Live`/`runS3`/`runS4`

Read the full file on GitHub · 162 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.

6d ago First seen · 162 lines · 2,164 tokens per session scan C 952cf8ffb42a

Subscribe to this mod's changes

cyvisguard AGENTS.md is an instructions file published in the GitHub repository flankerhqd/cyvisguard (56 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,164 tokens to every session, about $0.0108 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents agent-security ai-agents ai-security claude-code llm-security mcp

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

cyvisguard: Instructions file for Codex