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 nweii/agent-stuff --skill people-notesgit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/people-notes)<a href="https://agentmods.dev/skills/nweii/agent-stuff/people-notes"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/people-notes/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/nweii/agent-stuff/people-notes"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/people-notes.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 | $0.00036 | $0.01519 |
| Opus 5.5 | $0.00014 | $0.00608 |
| Sonnet 5.5 | $0.00007 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
people-notes 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 1mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
People notes
Prepare task-specific context from person notes and their linked records. Create or maintain a note only when the task calls for a vault change.
1. Choose the branch
Read the vault's AGENTS.md, then choose one branch from the user's task:
- Use — prepare context for work involving a person. This is the read-only default.
- Create — make a canonical person note when the user asks for one or the agreed vault task requires it.
- Maintain — reconcile an existing person note with newer evidence or requested corrections.
Link cleanup supports create and maintain; it is not a separate branch. A passing reference does not authorize note creation.
This step is complete when one branch is selected and the permitted read/write scope is clear.
2. Resolve the person
Search 04-Entities/ case-insensitively by canonical title and aliases. Treat body mentions and linked records as identity clues; a canonical note exists only when its title or aliases resolve the person.
Use relationship, organization, location, and source context to distinguish name variants or collisions. When two people share a full name, use a stable title qualifier such as Jordan Lee (Design) and display links such as [[Jordan Lee (Design)|Jordan Lee]].
This step is complete when one canonical note is identified, absence is confirmed, or unresolved candidates are reported.
3. Gather evidence
Start with the current conversation, the person note, and the records surfaced by ![[Related.base#Person]]. Read the recent records relevant to the task rather than dumping every backlink.
Reach beyond the vault only when the task needs more context or a freshness check. Granola meetings, Gmail threads, and verified public profiles are optional evidence sources. Continue with available evidence and report unavailable sources.
Track what each source establishes, its date, and any uncertainty. Treat Nathan's uncertainty as data; qualify or omit claims rather than resolving them by inference.
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.
- 1mo ago First seen · 120 lines · 36 tokens per session scan A 576b4e16ee46
people-notes is a skill published in the GitHub repository nweii/agent-stuff (10 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 1,519 once invoked, about $0.0001 per session on Opus 5.5. 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
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
Migrate
Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
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.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…