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.
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/setup-team-memory)<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>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 | $0.00046 | $0.04871 |
| Opus 5 | $0.00023 | $0.02436 |
| Sonnet 5 | $0.00009 | $0.00974 |
| Haiku 4.5 | $0.00005 | $0.00487 |
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" 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"
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.
- 4d ago First seen · 596 lines · 46 tokens per session scan B 0130e72f3701
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.
Other commands, from other repositories
setup-context
Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you.
brain
Set up or use your Professional Brain — init, ingest, recall, or review.
context-stats
Display context window usage and token statistics.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
meetings-list
List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching.
meetings-search
Search meeting transcripts and voice memos for people, topics, decisions, commitments, or remembered ideas. Use when the user asks what was discussed, decided, or said across their meeting history. Not for preparing an upcoming meeting; use $meetings-prep.