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-cligit 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-cli)<a href="https://agentmods.dev/skills/potpie-ai/potpie/potpie-cli"><img src="https://agentmods.dev/badge/skills/potpie-ai/potpie/potpie-cli/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-cli"><img src="https://agentmods.dev/badge/skills/potpie-ai/potpie/potpie-cli.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 | $0.00060 | $0.02500 |
| Opus 5.5 | $0.00024 | $0.01000 |
| Sonnet 5.5 | $0.00012 | $0.00500 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
potpie-cli 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Potpie CLI
Use this skill when the user is asking about the potpie command itself. For
ordinary project-memory context, prefer the relevant use-case skill first.
Setup And Scope
Install the published package with uv tool install potpie or
pip install potpie. Only inside the potpie source checkout — the repo whose
Makefile has a cli-install target — reinstall from source with:
make cli-install # UI build + stop old daemon + editable install
make cli-status
potpie doctor
Anywhere else there is no Makefile and make cli-status is a dead call; the
install facts come from uv tool list and which -a potpie. Do not use raw
uv tool install --editable … or pip install for day-to-day reinstalls of
the checkout. If potpie backend doctor names a missing driver, that is a
packaging answer — report what it names; do not treat it as a broken graph.
potpie status
potpie doctor
potpie --json doctor
uv tool list
which -a potpie
potpie login --api-key <key> --url <host>
potpie pot list
potpie pot use <pot-id-or-alias>
potpie --json pot info
potpie pot linked --repo current
potpie pot default set --repo current <pot-id-or-alias>
potpie --json source list
potpie source add repo .
potpie source add repo <owner/repo> --pot <pot>
login takes flags, not a positional key. potpie status is the one health
check: daemon, pot, backend readiness, claim counts and open quality findings
in a few lines; doctor adds the install, the backend's capabilities, the
repo → pot mapping, and the resource store and its index (resources and
resource_index rows).
Pot scope for graph …, resolve, search, record and the resource
commands resolves in this order:
- Explicit
--pot. - Repo-local default set by
source add repoorpot default set. - Registered repo source matching the current working tree path or
remote.origin.url. - Active pot from
potpie pot use. - Clear failure asking for setup, source registration, default selection, or
explicit
--pot.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +48 lines · +7 tokens per session 3471ecdebaaf
- 6d ago Changed · +65 lines · +3 tokens per session 586fbbe9b968
- 1mo ago First seen · 99 lines · 50 tokens per session scan A b4cd69cfe512
potpie-cli is a skill published in the GitHub repository potpie-ai/potpie (5,742 stars, last pushed 3d ago), licensed Apache-2.0. It adds 60 tokens to every session and 2,500 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
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.
mcp-apps-builder
MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
analyze-type-infer
A compiler analysis step that infers a symbol's type from its assignments. A type describes what kind of value something holds, such as a number, text, or Boolean value.
check-name-real
A name checker that verifies every required symbol has been declared. A symbol is a named program entity such as a variable or function.