Potpie is a tool that turns a software repository and its development history into a context graph for AI coding agents. Agents use that graph to answer codebase questions, plan changes, debug problems, and write code with project-specific information. The catalogue includes skills, hooks, commands, and a plugin for integrating Potpie into coding-agent workflows.
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 skills add potpie-ai/potpie --skill potpie-infra-architecturegit clone --depth 1 https://github.com/potpie-ai/potpieWrote 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.
[](https://agentmods.dev/skills/potpie-ai/potpie/potpie-infra-architecture)<a href="https://agentmods.dev/skills/potpie-ai/potpie/potpie-infra-architecture"><img src="https://agentmods.dev/badge/skills/potpie-ai/potpie/potpie-infra-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/potpie-ai/potpie/potpie-infra-architecture"><img src="https://agentmods.dev/badge/skills/potpie-ai/potpie/potpie-infra-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.01356 |
| Opus 5.5 | $0.00017 | $0.00542 |
| Sonnet 5.5 | $0.00009 | $0.00271 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
potpie-infra-architecture 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Potpie Infra Architecture
Use this skill when the task touches environments, adapters, deployment behavior, runtime config, service dependencies, production incidents, or architecture changes.
Fast Path
Share one discovery pass with other skills; reuse current reads and hook context for the same task, pot, and scope. Run broad resolve and an untyped entity lookup concurrently when the task names a service, environment, adapter, or dependency whose canonical key is unknown. Skip the lookup when a key is already known. For code changes, scoped preferences can run alongside both. Use a known explicit pot selector; resolve ambiguous routing before scoped retrieval and check returned pot IDs before combining results.
Broad context and conditional identity lookup:
potpie resolve "<the task, naming the service>"
potpie graph search-entities "<named service env adapter dependency>" --limit 10
Use the returned canonical service key for a neighborhood when the task needs
relationships or resolve leaves a gap; do not guess an anchor. For a direct
entity question, identity lookup then neighborhood can suffice without resolve.
The service:<service-name> below stands for that returned key. Start with
no --environment:
potpie graph read --subgraph infra_topology --view service_neighborhood --scope service:<service-name> --depth 2 --direction both --limit 20
The environment filter defaults to qualified_only: --environment prod
alone drops every unqualified edge — USES, DEFINED_IN, OWNED_BY — and
answers "talks to nothing". To exclude other environments, keep them explicitly:
potpie graph read --subgraph infra_topology --view service_neighborhood --scope service:<service-name>,include_unqualified_environment:true --environment <env> --depth 2 --direction both --limit 20
An empty neighborhood can mean missing relations, not a wrong key. Start with
--depth 2 --direction both; --direction accepts out, in or both, and
any other spelling is refused. A --depth past the view's maximum runs at the
maximum and says so. Alternatively, for
everything the graph holds about one service — decisions, preferences, timeline
and features beside the topology — use one flat list:
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.
- 9d ago Changed · +16 lines def7584652dc
- 13d ago Changed · +51 lines dcfc723d710a
- 1mo ago First seen · 71 lines · 43 tokens per session scan A 26c8abf56d91
potpie-infra-architecture is a skill published in the GitHub repository potpie-ai/potpie (5,768 stars, last pushed 4d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,356 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
oracle-mcp-server-helper
Wire the oracle-database-mcp-server into a Python project so an LLM agent can call listtables / describetable / runsql / vectorsearch at inference time. Handles install, stdio launch, and LangChain tool conversion via langchain-mcp-adapters. Use whenever a project needs a Grok 4 / GPT-class agent that talks to a live…
langchain_patterns
Implement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.
langchain_patterns
Implement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.
scope-creep-detector
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too…
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
azure-search-documents-ts
Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents). Use when creating/managing indexes, implementing vector/hybrid search, semantic ranking, or building agentic retrieval with knowledge bases.