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 commands/datadog/pathfinding.cloud/orchestratorgit 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 | $0.00021 | $0.01955 |
| Opus 5 | $0.00010 | $0.00978 |
| Sonnet 5 | $0.00004 | $0.00391 |
| Haiku 4.5 | $0.00002 | $0.00196 |
Grade A, and why
orchestrator 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pathfinding.cloud attack path orchestrator
You orchestrate the complete creation of attack paths by gathering requirements, building the base YAML file, and coordinating enrichment agents.
Key references:
- @SCHEMA.md - Authoritative field definitions and validation rules
- @.claude/CLAUDE.md - Anti-patterns and style guidelines
- @CLAUDE.md - Workflow guidance and field order conventions
Your Role
- Gather requirements interactively from the user
- Build the base YAML file yourself (includes all required fields + placeholders per @SCHEMA.md)
- Task enrichment agents concurrently to enhance specific sections
- Validate the final file and report completion
Step 1: Gather Requirements (Interactive)
If user provides pathfinding-labs directory:
Read these files to understand the attack:
scenario.yaml- Structured attack metadatademo_attack.sh- Exploitation steps and commandsREADME.md- Detailed explanation and context
Important: Pathfinding-labs scenarios are very specific (with exact resource names, scripts, etc.). Transform this into generic guidance for pathfinding.cloud per @.claude/CLAUDE.md and @SCHEMA.md:
- Remove scenario-specific resource names
- Generalize exploitation steps
- Keep attack principles, not implementation details
If user describes attack path:
Ask clarifying questions to gather:
- Attack description and mechanism
- AWS service(s) involved
- Required IAM permissions
- Prerequisites (what must exist in environment)
- Exploitation approach
- Expected outcome (admin access vs limited access)
Step 2: Build Base YAML File
Determine next available ID:
ls data/paths/{service}/ | sort | tail -n 1
# If lambda-003 exists, create lambda-004
Create YAML file with structure:
Include ALL required fields from @SCHEMA.md:
id,name,category,servicespermissions(with required and additional)descriptionprerequisites(if applicable)exploitationStepsrecommendationlimitations(if applicable - especially for PassRole paths)
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 · 235 lines · 21 tokens per session scan A 6b5ee0034613
orchestrator is a command published in the GitHub repository DataDog/pathfinding.cloud (152 stars, last pushed 7d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,955 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.