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 skills add michelgrolet/people-memory-mcp --skill setup-people-memorygit clone --depth 1 https://github.com/michelgrolet/people-memory-mcpWrote 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/skills/michelgrolet/people-memory-mcp/setup-people-memory)<a href="https://agentmods.dev/skills/michelgrolet/people-memory-mcp/setup-people-memory"><img src="https://agentmods.dev/badge/skills/michelgrolet/people-memory-mcp/setup-people-memory/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.
<a href="https://agentmods.dev/skills/michelgrolet/people-memory-mcp/setup-people-memory"><img src="https://agentmods.dev/badge/skills/michelgrolet/people-memory-mcp/setup-people-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00107 | $0.00906 |
| Opus 5 | $0.00053 | $0.00453 |
| Sonnet 5 | $0.00021 | $0.00181 |
| Haiku 4.5 | $0.00011 | $0.00091 |
Grade A, and why
setup-people-memory 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up People Memory
Configure the whole path from conversation to private database. Keep credentials out of chat output, Git, browser code, and shell history where possible.
1. Inspect before asking
- Check whether the
people-memoryMCP tools are already present. - If present, call
graph_status. Offer repair or reconfiguration instead of reinstalling blindly. - Detect the current agent,
uv, Supabase CLI, Docker-compatible runtime, and browser tools. - Locate a cloned
people-memory-mcprepo if one exists.
Do not claim a component works because its config file exists. Verify the MCP with graph_status.
2. Ask the deployment choice
Ask one compact question with these options:
- Hosted Supabase, recommended for a free cloud backend, Auth, REST, and browser UI.
- Local Supabase, recommended when all contact data must remain on the machine.
- Existing PostgreSQL, for users who already operate a database. Explain that the UI then needs the optional API or a compatible auth/REST layer.
Read references/deployment.md for the chosen path. Do not load the other paths.
3. Set the owner and secrets
- Store the PostgreSQL URL in
~/.config/people-memory/.envwith mode0600. - Generate an API token if the optional REST API will run.
- Set
app_settings.owner_emailto the account that may open the hosted UI. - Put only the Supabase URL and publishable key in
web/config.js. - Never put a service-role key or PostgreSQL URL in the browser.
4. Connect the current agent
Prefer the user's existing agent. Add the stdio MCP through that agent's supported command or config. For Codex and Claude Code, use the exact current commands in the repository README. Start a fresh session after changing MCP config.
Offer to install the durable memory rule from templates/AGENTS.md or templates/CLAUDE.md. Ask
before changing a global user instruction file. Preserve existing content and add one clearly named
section.
If the user has no agent, offer a minimal workspace containing the matching template and connect it to Codex or Claude Code. Do not build a custom agent runtime unless they ask for one.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 87 lines · 107 tokens per session scan A c0208abd90e6
setup-people-memory is a skill published in the GitHub repository michelgrolet/people-memory-mcp (1 stars, last pushed 16d ago), licensed MIT. It adds 107 tokens to every session and 906 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
claude-memory
Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…
explorer
Build and modify Studio Explorer surfaces, including notebooks, chats, SQL snippets, query cells, and their shared toolbar patterns.
supabase
Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies…
supabase-postgres-best-practices
Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the…
omnigraph
Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…
srtd-cli
This skill should be used when the user mentions "srtd", "sql templates", "migrations-templates", "live reload sql", "supabase functions", when working with files in supabase/migrations-templates/, when .buildlog.json or srtd.config.json is detected, or when writing Postgres functions/views/triggers for Supabase.