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 LuisUrrutia/skills --skill people-memorygit clone --depth 1 https://github.com/LuisUrrutia/skillsWrote 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/luisurrutia/skills/people-memory)<a href="https://agentmods.dev/skills/luisurrutia/skills/people-memory"><img src="https://agentmods.dev/badge/skills/luisurrutia/skills/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/luisurrutia/skills/people-memory"><img src="https://agentmods.dev/badge/skills/luisurrutia/skills/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 | $0.00058 | $0.00688 |
| Opus 5 | $0.00029 | $0.00344 |
| Sonnet 5 | $0.00012 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
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 10d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
People Memory
Purpose
Keep useful relationship memory in Obsidian People profiles without writing noise. This skill is a concise entry point, with detailed matching, prompts, and QA kept in the companion docs.
Quick Start
- Trigger on any person mention, including full names, aliases, nicknames, and contextual references such as
my manager,my cousin, orthe founder I met last week. - Load REFERENCE.md before matching or updating.
- Search existing profiles under
06 - People/by filename, aliases, known names, and relevant context. - Decide whether the write gate passes before editing.
- Use
Assets/Templates/t.people.mdas the source template convention for new profiles. - Load QA.md before reporting completion after any write.
Core Workflow
- Detect the person mention or explicit create/update request.
- Match the person using REFERENCE.md, including confidence and contextual reference rules.
- If creation or a prompt is needed, use TEMPLATES.md for the exact profile shape and question wording.
- Write only when allowed by the write gate.
- Preserve existing profile structure and fields while making the smallest useful change.
- Run the QA checklist before responding.
Write Gate
Triggering is broad. Writing is narrow.
Write only when one of these is true:
- The user explicitly asks to create or update a person profile.
- The conversation adds new useful relationship memory, such as identity, contact details, role, company, alias, where-met context, preferences, commitments, follow-ups, or meaningful conversation notes.
Do not write when:
- The person is only mentioned in passing.
- The fact is already present in the matched profile.
- The information is vague, unresolved, or not useful as durable relationship memory.
Ask Instead Of Writing
Ask one direct clarification question, then stop, when:
- A name, alias, or nickname matches multiple plausible profiles.
- A contextual reference does not resolve to exactly one confident person.
- Creation is requested but the full name or one context clue is missing.
- The update would overwrite an existing
email,phone,linkedin, orcompanyvalue.
What ships with it
4 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.
- 10d ago First seen · 71 lines · 58 tokens per session scan A 51f906ebfff5
people-memory is a skill published in the GitHub repository LuisUrrutia/skills (2 stars, last pushed 17d ago), licensed MIT. It adds 58 tokens to every session and 688 once invoked, about $0.0003 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
google-drive-knowledge-bank
Build and query a knowledge bank from Google Docs meeting notes. Use when the user wants to ingest meeting notes from Google Drive, or when answering questions about previously ingested meeting notes. Trigger on phrases like "ingest my meeting notes", "load meeting notes from folder", "what did we discuss about X"…
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
usage-audit
Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.
memory-md-management
Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use when user asks to check, audit, update, improve, fix, maintain, or validate project memory files. Also triggers for "project memory optimization", "CLAUDE.md…