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-repo-baselinegit 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-repo-baseline)<a href="https://agentmods.dev/skills/potpie-ai/potpie/potpie-repo-baseline"><img src="https://agentmods.dev/badge/skills/potpie-ai/potpie/potpie-repo-baseline/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-repo-baseline"><img src="https://agentmods.dev/badge/skills/potpie-ai/potpie/potpie-repo-baseline.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 | $0.00075 | $0.01452 |
| Opus 5 | $0.00037 | $0.00726 |
| Sonnet 5 | $0.00015 | $0.00290 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
potpie-repo-baseline 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 12d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Potpie Repo Baseline
Use this skill when the user asks to ingest, refresh, establish, or deeply understand what a repository is and how it works.
Procedure
- Resolve the pot and source:
potpie --json pot info
potpie --json source list
potpie source add repo . --pot <pot-id-or-name>
Source registration records metadata only. It does not ingest or scan.
- Discover the live graph contract:
potpie --json graph status
potpie --json graph catalog --task "deep repo baseline"
potpie --json graph describe features --view feature_context --examples
potpie --json graph describe infra_topology --view service_neighborhood --examples
potpie --json graph describe decisions --view preferences_for_scope --examples
- Create todos for the baseline lanes: docs/product, repo map, runtime/deploy, API/data/integrations, preferences/workflows, synthesis, identity resolution, write, verify.
- Read authored sources first, then inspect source files that are authoritative for durable facts: routes, service clients, adapters, deployment targets, API contracts, model/datastore usage, and test/workflow commands.
- Resolve identity before writing:
potpie graph search-entities "<repo service feature>" --limit 10
potpie graph search-entities "<service>" --type Service --environment prod --limit 10
- Write one or more semantic mutation batches:
potpie --json graph propose --file mutation.json
potpie --json graph commit <plan_id> --verify
potpie --json graph history --plan <plan_id>
graph mutation-template --kind repo-baseline is an optional skeleton helper;
trust graph catalog and graph describe ... --examples for the live contract.
Deep Baseline Mode
Use this mode whenever the user says "ingest repo", "deeply understand", "baseline this repo", or asks for broad repo memory.
- Product and docs:
- README, docs, ADRs, runbooks, contributing guide, package metadata, public docs, linked websites.
- Capture purpose, app type, domain vocabulary, explicit features, decisions, preferences, and workflows.
- Repo map:
- Manifests, top-level apps/packages, framework config, route/API entrypoints, generated API specs, tests.
- Capture services/modules only when a source clearly supports them.
- Runtime and deploy:
- Dockerfiles, compose, Kubernetes, Terraform, CI workflows, deploy scripts, environment templates, feature flags.
- Capture environments, deploy shape, config variables, release/test workflows, and ownership when explicit.
- API, data, and integrations:
- Service clients, adapters, auth providers, queues, datastore/model usage, external API clients.
- Capture APIContract, DataStore, Adapter, Dependency, and integration facts with file/doc evidence.
- Preferences and local workflows:
- Contribution docs, lint/test configs, Makefiles, package scripts, PR templates, code comments that explicitly state policy.
- Record only reusable explicit preferences.
- Synthesis:
- Build an evidence matrix before writing. Split high-confidence facts from uncertain observations. Use inbox for useful but weak findings.
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.
- 12d ago First seen · 154 lines · 75 tokens per session scan A 09d6ff500b3f
potpie-repo-baseline is a skill published in the GitHub repository potpie-ai/potpie (5,718 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 1,452 once invoked, about $0.0004 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 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…
astra-vector-backend
Design Astra DB Data API and vector-search backends for retrieval, metadata filtering, and LangChain-compatible stores.
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…
status
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.