setup-team-memory

setup-team-memory is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 46 tokens per session (4,871 once invoked), scanned B, original, MIT.

A one-step setup tool for sharing development memory between team members using claude-mem and claude-mem-sync. It installs, configures, checks prerequisites, and verifies the setup when possible.

In plain words
What is it for?
Use it to prepare and verify a team memory system, including checks for Node.js, Bun, GitHub CLI, npx, and Python.
Why use it?
It reduces the manual work of setting up shared project memory and checking whether each required tool is available. It also makes repeated runs safe by skipping completed steps.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the SlashCommand tool.

Good fit Use it to prepare and verify a team memory system, including checks for Node.js, Bun, GitHub CLI, npx, and Python.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kumaran-is/claude-code-onboarding/setup-team-memory
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.

Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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.

agentmods badge for setup-team-memory

README.md
[![agentmods](https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/setup-team-memory.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/setup-team-memory)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/setup-team-memory"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/setup-team-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,871 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.04871
Opus 5 $0.00023 $0.02436
Sonnet 5 $0.00009 $0.00974
Haiku 4.5 $0.00005 $0.00487

Measured 4d ago against content hash 0130e72f3701, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

setup-team-memory 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -c "claude-mem" ~/.claude/settings.json 2>/dev/null || echo "0"

Makes network callslowCapability

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

curl -s --max-time 3 http://localhost:37777/health 2>/dev/null && echo "" || echo "NOT_RUNNING"
.claude/commands/setup-team-memory.md · 596 lines

How it starts

The opening of the file, as written. The whole thing — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup Team Memory — claude-mem + claude-mem-sync

One-shot installer and verifier for your team memory stack. Reference doc: docs/tools/claude-mem-team-memory.md


Behaviour Rules

  • Every step checks current state BEFORE acting — skip if already done
  • Every action requires proof output before marking ✅
  • If any prerequisite is missing → STOP immediately, report exactly what is needed
  • Running this command twice must be safe (idempotent)
  • Do NOT touch .claude/rules/, CLAUDE.md, or any existing hooks

Step 1 — Detect Prerequisites

Run all detection checks. Collect results before proceeding.

echo "=== PREREQUISITE CHECK ==="

echo -n "Node.js: "
node --version 2>/dev/null || echo "MISSING"

echo -n "Bun: "
bun --version 2>/dev/null || echo "MISSING"

echo -n "GitHub CLI: "
gh --version 2>/dev/null | head -1 || echo "MISSING"

echo -n "npx: "
npx --version 2>/dev/null || echo "MISSING"

echo -n "Python3: "
python3 --version 2>/dev/null || echo "MISSING"

Gate: If Node.js is missing or version < 18, OR Bun is missing, OR gh is missing → STOP. Report exactly:

BLOCKED — Prerequisites missing:
- [item]: install with [exact command]

Cannot proceed until prerequisites are resolved.

Do not continue to Step 2 until all prerequisites pass.


Step 2 — Detect Current Installation State

Run all detection checks and build a state table.

echo "=== CURRENT STATE DETECTION ==="

echo -n "claude-mem worker: "
curl -s --max-time 3 http://localhost:37777/health 2>/dev/null && echo "" || echo "NOT_RUNNING"

echo -n "claude-mem DB: "
ls -lh ~/.claude-mem/claude-mem.db 2>/dev/null || echo "MISSING"

echo -n "claude-mem hooks in settings: "
grep -c "claude-mem" ~/.claude/settings.json 2>/dev/null || echo "0"

echo -n "claude-mem settings.json: "
ls ~/.claude-mem/settings.json 2>/dev/null || echo "MISSING"

echo -n "mem-sync CLI: "
mem-sync --version 2>/dev/null || echo "MISSING"

echo -n "mem-sync config: "
ls ~/.claude-mem-sync/config.json 2>/dev/null || echo "MISSING"

echo -n ".claude/memories/ folder: "
PROJ=$(git rev-parse --show-toplevel)
ls -d $PROJ/.claude/memories/ 2>/dev/null || echo "MISSING"

echo -n "GitHub Actions workflow: "
ls $PROJ/.github/workflows/merge-memories.yml 2>/dev/null || echo "MISSING"

echo -n ".gitignore entry: "
grep -c "memories/contributions" $PROJ/.gitignore 2>/dev/null || echo "0"

echo -n "Cron/launchd schedule: "
launchctl list 2>/dev/null | grep -i mem-sync | head -1 || crontab -l 2>/dev/null | grep mem-sync | head -1 || echo "NOT_SCHEDULED"

Read the full file on GitHub · 596 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.

  1. 4d ago First seen · 596 lines · 46 tokens per session scan B 0130e72f3701

Subscribe to this mod's changes

setup-team-memory is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 4,871 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.