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/datadog/pathfinding.cloud/claude-mdgit clone --depth 1 https://github.com/DataDog/pathfinding.cloudWhat 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 | $0.03837 | $0.03837 |
| Opus 5 | $0.01919 | $0.01919 |
| Sonnet 5 | $0.00767 | $0.00767 |
| Haiku 4.5 | $0.00384 | $0.00384 |
Grade A, and why
pathfinding.cloud CLAUDE.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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
When to Use Each File
- CLAUDE.md (this file): Workflow guidance, commands, development tasks, and quick references
- SCHEMA.md: Authoritative field definitions, validation rules, and format specifications
- .claude/CLAUDE.md: Anti-patterns, style guide, and contribution-specific guidance
Rule of thumb: Check SCHEMA.md for "what does field X mean?", check this file for "how do I do task Y?"
Project Overview
pathfinding.cloud is a comprehensive, community-maintained library documenting AWS IAM privilege escalation paths. The project consists of:
- Data Layer: Structured YAML files documenting each privilege escalation path
- Validation Layer: Python scripts to validate YAML against schema
- Website Layer: Static HTML/CSS/JS site for browsing paths
- CI/CD Layer: GitHub Actions for validation and deployment
Terminology: Parent/Child vs Primary/Variant
We use different terminology in different contexts for clarity and semantic meaning:
In YAML Files and Code
parentfield: Points to the parent path (e.g.,parent.id: iam-002)- Why: Concise, follows common data structure conventions, natural for hierarchical references
In UI and Documentation
- "Primary Technique": The foundational/original technique (what YAML calls the "parent")
- "Variant": A modification that expands applicability by removing prerequisites (what YAML calls the "child")
- Why: Semantic clarity - "variant" explains WHAT it is, not just that there's a hierarchy
Key Concepts
- Primary techniques have no
parentfield - they are the foundational attacks - Variant techniques have a
parentfield withidandmodification - Variants add required permissions that remove prerequisites from the primary technique
- Example: IAM-002 (primary) requires < 2 keys. IAM-003 (variant) adds DeleteAccessKey to work even with 2 keys.
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.
- 2d ago First seen · 377 lines · 3,837 tokens per session scan A a6b5ee7a5e8f
pathfinding.cloud CLAUDE.md is an instructions file published in the GitHub repository DataDog/pathfinding.cloud (152 stars, last pushed 7d ago), licensed Apache-2.0. It adds 3,837 tokens to every session, about $0.0192 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
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.