potpie-feature

A command for loading Potpie project context before feature work. Potpie is a tool that stores project preferences, architecture, decisions, and relationships in a searchable graph.

In plain words
What is it for?
Use it before building a feature, especially when the change involves services, deployment, adapters, or runtime behavior.
Why use it?
It helps feature work follow the project's existing preferences and understand affected services before changes are made.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/potpie-ai/potpie/potpie-feature
Clone the repo
git clone --depth 1 https://github.com/potpie-ai/potpie

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00215
Opus 5 $0.00000 $0.00108
Sonnet 5 $0.00000 $0.00043
Haiku 4.5 $0.00000 $0.00021

Measured yesterday against content hash 37376dd13143, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

potpie-feature 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 yesterday.

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.

potpie/cli/templates/claude_bundle/.claude/commands/potpie-feature.md · 18 lines

What it actually says

Use Potpie context before feature work. Load potpie-project-preferences first, and load potpie-infra-architecture when the change touches services, deployment, adapters, or runtime behavior.

If the potpie CLI is available, read the graph directly:

potpie --json graph catalog --task "feature work in repo:<owner/repo>"
potpie --json graph describe decisions --view preferences_for_scope --examples
potpie graph read --subgraph decisions --view preferences_for_scope --scope repo:<owner/repo>
potpie graph read --subgraph decisions --view active_decisions --scope repo:<owner/repo>
potpie graph read --subgraph infra_topology --view service_neighborhood --scope service:<name> --depth 2

Expand the user's request into a good retrieval --query/query (add symptoms and synonyms a future searcher would type). Inspect coverage, freshness, quality, fallbacks, open conflicts, and source refs before relying on the result.

Changes

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.

  1. yesterday First seen · 18 lines · 0 tokens per session scan A 37376dd13143

Subscribe to this mod's changes

potpie-feature is a command published in the GitHub repository potpie-ai/potpie (5,702 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 215 tokens. 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.