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 graph-mutation-plangit 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/graph-mutation-plan)<a href="https://agentmods.dev/skills/potpie-ai/potpie/graph-mutation-plan"><img src="https://agentmods.dev/badge/skills/potpie-ai/potpie/graph-mutation-plan/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/graph-mutation-plan"><img src="https://agentmods.dev/badge/skills/potpie-ai/potpie/graph-mutation-plan.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 | $0.00051 | $0.01231 |
| Opus 5.5 | $0.00020 | $0.00492 |
| Sonnet 5.5 | $0.00010 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
graph-mutation-plan 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 7d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composing an apply_graph_mutations plan
Call apply_graph_mutations(plan, event_id, summary) once per logical group of
mutations. The plan is idempotent on stable entity_keys, so a retried plan
converges rather than duplicating. Every structural mutation must stay inside
the given pot_id — never reference another pot.
Plan fields
summary: one-line description of what this plan records.episodes:{name, episode_body, source_description, reference_time?}— narrative/source text to retain (e.g. a PR body, a note).entity_upserts:{entity_key, labels, properties}.edge_upserts:{edge_type, from_entity_key, to_entity_key, properties}.edge_deletes:{edge_type, from_entity_key, to_entity_key}.invalidations:{reason, target_entity_key?, edge_type?, from_entity_key?, to_entity_key?}.evidence:{kind, ref, metadata?}— what grounds this plan.confidence: float | null.warnings: list[str] — anything you could not confirm.
Stable entity_key cookbook
Use these so re-ingestion (and a later live webhook for a backfilled artifact) upserts the same node:
Use the exact key prefixes from the canonical ingestion ontology in your
instructions and reuse identities found by graph reads. PRs and issues are
Activity entities with source identifiers, e.g.
activity:github:pr:<owner>/<repo>:<n>; implementation paths use CodeAsset,
e.g. code:<repo>:<path>. Provider references such as github:pr:... are
evidence refs, not a substitute for a canonical entity key.
When no pattern fits, mint a deterministic key from stable identifiers in the source (never a random id, never a timestamp), so the same fact re-keys the same way.
Canonical vocabulary
Always give an entity at least one canonical label — never only generic
Entity. Labels/edges outside the canonical vocabulary are downgraded
automatically (entities → Document / Observation, edges → RELATED_TO), so
prefer a canonical type when one fits.
The complete public entity/predicate vocabulary is generated from
potpie_context_engine.core.ontology and supplied in your instructions. Use its
allowed endpoint pairs and exact prefixes instead of a remembered subset.
Capabilities use Feature with supported PROVIDES/IMPLEMENTED_IN links;
dependencies use topology relations; choices with rationale use Decision;
only explicit future-facing prescriptions use Preference/Policy.
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.
- 7d ago Changed 0b21f0d72e19
- 1mo ago First seen · 111 lines · 51 tokens per session scan A a7e3c0a39b7a
graph-mutation-plan is a skill published in the GitHub repository potpie-ai/potpie (5,747 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,231 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.
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
build-paths-advanced
Scaffold an agent system where Oracle AI DB is the only state store, composed from the build-paths/skills/ building-block library. Stack — langchain-oracledb + oracle-database-mcp-server + in-DB ONNX embeddings + OCI GenAI Grok 4 + Open WebUI. Three projects — production-feeling NL2SQL+RAG hybrid analyst…
build-paths-intermediate
Scaffold a Grok-4 tool-calling agent over an Oracle schema using langchain-oracledb + oracle-database-mcp-server + in-DB ONNX embeddings (registered MiniLM model, no external embedding API) + Open WebUI. For users who've built RAG before and want to rebuild it on the production-feeling Oracle stack.
soccer-workshop-setup
Bootstrap the soccer analytics agent workshop. Starts the Oracle AI Database Free container, applies schema, loads the FIFA dataset, optionally trains models, populates LangChain OracleVS hybrid retrieval plus semantic memory, applies LangGraph OracleDB observability, and verifies OCI GenAI access. Use when starting…