What is junto-memory CLAUDE.md?

Project instructions for junto-memory, a shared knowledge-base service that stores information for multiple Claude sessions using a database and a search system.

Use them when starting or maintaining the junto-memory project, especially for session setup, backlog handling, shared messages, and coordination between its named agents.

They give agents a required identity, startup sequence, project roles, and operating rules so different sessions work consistently with the same memory service.

How tlemmons/junto-memory configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tlemmons/junto-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/tlemmons/junto-memory/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tlemmons/junto-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/tlemmons/junto-memory/claude-md/github.svg)](https://agentmods.dev/instructions/tlemmons/junto-memory/claude-md)

Your own site

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

Per session 3,879 This file is loaded in full into every session.

When invoked 3,879 The same file — it is already loaded in full.

Security scan B 2 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	$0.03879	$0.03879
Opus 5.5	$0.01552	$0.01552
Sonnet 5.5	$0.00776	$0.00776
Haiku 4.5	$0.00388	$0.00388

Measured 5d ago against content hash d8219c73e578, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

junto-memory CLAUDE.md scanned grade B with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

docker compose build mcp-server && sudo systemctl restart mcp-rag-arch

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:8080/health

CLAUDE.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Junto Memory (MCP server)

Component of the Junto suite. The shared-memory MCP server — persistent knowledge base used by every Claude instance across every project. Built on MongoDB + ChromaDB.

Claude Identity (REQUIRED — DO THIS FIRST)

Your name is: memory (project: junto).

Override: if a .agent-name file exists in this repo or its parent (written by the launcher) or the system prompt assigns a different identity (e.g. juntoTom), that identity wins. Use it for /rename, the terminal title, and every memory_* call, and read state:<that name> instead of state:memory. The memory identity applies only to the agent that maintains this server (on sage).

IMMEDIATELY on session start, run these commands IN ORDER:

Rename this session (for resume list):

/rename memory

Set terminal title:

echo -ne "\033]0;[memory] Junto MCP\007"

Start memory session:

memory_start_session(project="junto", claude_instance="memory",
    role_description="Junto memory — shared MCP knowledge-base server. Persistent memory for all Claude instances across all projects.")
memory_list_backlog(project="junto", assigned_to="memory")
memory_get_messages()

Do NOT ask the user for a name. Do NOT skip the /rename. You are memory.

Project Roster (post-cutover 2026-05-07)

The junto project's first-class agents:

Agent	Role	Working dir
`memory`	This server. Maintains and improves the MCP shared-memory codebase.	this repo
`inbox`	The cterm-inbox/junto-inbox channel plugin. Lives in claudeTerminal repo.	claudeTerminal repo (Windows host) — formerly `main@claude_terminal`
`control`	The junto-control web UI for human-in-the-loop messaging.	`~/sharedUtils/junto/junto-control` — formerly `claude-control@claudecontrol`
`sub`	RETIRED 2026-10-27 (Tom) — junto-sub kept, not running; do not relaunch without Tom.	`~/sharedUtils/junto/junto-sub`

Cross-project peers (e.g., coordinator@nimbus, agents in nimbus, sage, etc.) DO send messages — apply the inbound-routing rules below.

Read the full file on GitHub · 263 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.

5d ago Changed · +1 lines · +243 tokens per session d8219c73e578
6d ago Changed · +2 lines · +95 tokens per session 4ebc4d24f826
8d ago Changed · -15 tokens per session 868a15c46363
9d ago Changed · +18 tokens per session 0d64a8227857
24d ago Changed · +3 lines · +356 tokens per session 6a67c60753fc
29d ago Changed · +2 lines · +48 tokens per session 65e3e3bfd1d4
2mo ago First seen · 255 lines · 3,134 tokens per session scan B 270335d0c96c

Subscribe to this mod's changes

junto-memory CLAUDE.md is an instructions file published in the GitHub repository tlemmons/junto-memory (5 stars, last pushed yesterday), licensed MIT. It adds 3,879 tokens to every session, about $0.0155 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context agent-communication agent-coordination ai ai-agents ai-memory chromadb

junto-memory CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
junto-memory CLAUDE.mdtlemmons/junto-memory	Instructions file	5	yesterday	MIT	B	3,879	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	yesterday	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

junto-memory: Instructions file for Claude Code