What is episodic-memory CLAUDE.md?

Project instructions for episodic-memory, a Claude Code plugin that searches earlier conversations by meaning. They document the project layout, build and test commands, generated files, and release version rules.

Use them when developing or releasing episodic-memory, especially when editing its TypeScript source, running tests, rebuilding files, or updating versions.

They help an agent change the plugin safely while keeping its source, built files, tests, and version information consistent.

How obra/episodic-memory configures Claude Code

About the project

Episodic Memory is a semantic search system for conversations held with Claude Code and Codex, helping agents retrieve earlier discussions, decisions, patterns, and their reasoning. Coding agents use it to maintain context across sessions and avoid repeating explored or rejected approaches, with the catalogue packaging the project's memory workflow and integrations.

obra/episodic-memory · 499 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to obra/episodic-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/obra/episodic-memory/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/obra/episodic-memory

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/obra/episodic-memory/claude-md/github.svg)](https://agentmods.dev/instructions/obra/episodic-memory/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/obra/episodic-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/obra/episodic-memory/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/obra/episodic-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/obra/episodic-memory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,687 This file is loaded in full into every session.

When invoked 1,687 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01687	$0.01687
Opus 5.5	$0.00675	$0.00675
Sonnet 5.5	$0.00337	$0.00337
Haiku 4.5	$0.00169	$0.00169

Measured 2mo ago against content hash 7da3b51a2b57, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

episodic-memory CLAUDE.md 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 2mo 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.

CLAUDE.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions: episodic-memory

A Claude Code plugin that gives semantic search across past Claude Code conversations. This file holds the conventions an AI assistant needs to work on this codebase safely.

Quick orientation

TypeScript source in src/, compiled to dist/ by tsc && esbuild. Both are committed.
CLI entry points in cli/ (Node.js wrappers — no bash).
MCP server is dist/mcp-server.js, launched by cli/mcp-server-wrapper.js from the plugin manifest.
Tests live in test/, run via vitest.
Generated files live in dist/ and src/version.ts. The latter is gitignored; never edit it.

Build and test

npm test          # full suite, runs prebuild step that generates src/version.ts
npm run build     # tsc + esbuild bundle
npm run generate-version   # writes src/version.ts from package.json

The prebuild and pretest hooks both regenerate src/version.ts. After source changes that touch the MCP server or any imported module, run npm run build so dist/ reflects source. Commit dist/ alongside src/.

Version management

Three files hold the plugin version, all kept in lockstep:

package.json
.claude-plugin/plugin.json
.claude-plugin/marketplace.json (plugins[0].version)

Plus a fourth thing outside this repo:

../superpowers-marketplace/.claude-plugin/marketplace.json (the user-visible install registry)

To bump in this repo:

./scripts/bump-version.sh X.Y.Z         # updates all three local files
./scripts/bump-version.sh --check       # report current versions
./scripts/bump-version.sh --audit       # scan for stale references

The script reads .version-bump.json for the file list and audit excludes. MCP server identity (the version field in new Server({...}) in src/mcp-server.ts) is derived from src/version.ts, which the prebuild script generates from package.json — keep that pipeline in place; never hardcode the version.

Release engineering

Read the full file on GitHub · 130 lines

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.

2mo ago First seen · 130 lines · 1,687 tokens per session scan A 7da3b51a2b57

Subscribe to this mod's changes

episodic-memory CLAUDE.md is an instructions file published in the GitHub repository obra/episodic-memory (499 stars, last pushed 1mo ago), licensed MIT. It adds 1,687 tokens to every session, about $0.0067 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.

Building agents

episodic-memory CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
episodic-memory CLAUDE.mdobra/episodic-memory	Instructions file	499	1mo ago	MIT	A	1,687	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

episodic-memory: Instructions file for Claude Code