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 agentmods add commands/potpie-ai/potpie/potpie-recordgit 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/commands/potpie-ai/potpie/potpie-record)<a href="https://agentmods.dev/commands/potpie-ai/potpie/potpie-record"><img src="https://agentmods.dev/badge/commands/potpie-ai/potpie/potpie-record.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00257 |
| Opus 5 | $0.00000 | $0.00129 |
| Sonnet 5 | $0.00000 | $0.00051 |
| Haiku 4.5 | $0.00000 | $0.00026 |
Grade A, and why
potpie-record 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 5d 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.
What it actually says
Record durable Potpie learnings after useful work.
Choose the workflow skill first: potpie-project-preferences,
potpie-infra-architecture, potpie-change-timeline, potpie-debug-memory, or
potpie-source-ingestion.
First resolve identity so you link to existing nodes, not duplicates:
potpie graph search-entities "<entity name>" --type <Service|BugPattern|...>
Then write through the V2 graph plan workflow:
potpie --json graph propose --file mutation.json
potpie --json graph commit <plan_id> --verify
potpie --json graph history --plan <plan_id>
Capture:
- decisions
- fixes (with the bug they resolve)
- bug patterns
- preferences
- workflows
- incident summaries
- source-ingested timeline/doc/reference events
Write the description for retrieval, not display. Include the symptoms,
synonyms, and scope a future searcher would type — a vague card means the fact never
resurfaces. Pick an honest truth class (agent_claim when you inferred it), keep the
record compact and source-reference-first, and never hard-delete — end validity or
retract instead.
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.
- 5d ago First seen · 36 lines · 0 tokens per session scan A 8ec9c00249a6
potpie-record is a command published in the GitHub repository potpie-ai/potpie (5,710 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 257 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.
Other commands, from other repositories
xp-builder
Run the real Limitless XP Builder backend instead of simulating the session.
xp-answer
Send the learner's next answer into the currently active XP session.
xp-debrief
Run the real Limitless XP Debrief backend instead of simulating scoring in chat.
xp-finish
Finish the active XP session using the real backend.
xp-hint
Use the active XP session and request a hint from the real backend.
xp-status
Show the active XP session status from the real backend.