ppl

ppl is a skill for Claude Code from eliransu/digital-brain. It costs 137 tokens per session (3,056 once invoked), scanned A, original, MIT.

A skill that maintains person pages in an Obsidian wiki, a linked collection of Markdown notes, for people you work with.

In plain words
What is it for?
Use it to add or edit a person's page with their role, relationship, team, and tags, while updating the relevant indexes and log.
Why use it?
It turns scattered references to colleagues into consistent, reusable records and links their names in later wiki updates.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the digital-brain plugin — 18 skills, 5 commands, 2 agents, 3 hooks shipped together

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.

agentmods
npx agentmods add skills/eliransu/digital-brain/ppl
Any agent
npx skills add eliransu/digital-brain --skill ppl
Clone the repo
git clone --depth 1 https://github.com/eliransu/digital-brain

Made for: Claude Code.

Or install digital-brain, the plugin that ships this one along with the rest of its 18 skills, 5 commands, 2 agents, 3 hooks.

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 ppl

README.md
[![agentmods](https://agentmods.dev/badge/skills/eliransu/digital-brain/ppl.svg)](https://agentmods.dev/skills/eliransu/digital-brain/ppl)
Your own site
<a href="https://agentmods.dev/skills/eliransu/digital-brain/ppl"><img src="https://agentmods.dev/badge/skills/eliransu/digital-brain/ppl.svg" alt="Measured on agentmods" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,056 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00137 $0.03056
Opus 5 $0.00068 $0.01528
Sonnet 5 $0.00027 $0.00611
Haiku 4.5 $0.00014 $0.00306

Measured 5d ago against content hash 2adb1f7c038b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ppl 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 5d 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.

skills/ppl/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ppl: People Manager for the Brain Vault

you works with a lot of people. This skill turns "Alice Perl is a Security Researcher in my team" into a permanent, cross-referenced wiki entity. Once filed, every future synthesis, daily sync, save, or ingest links the mention to the person's page.

The wiki compounds. People compound too.


Vault Layout

  • Vault root: ~/digital-brain/
  • People folder: wiki/entities/people/ (create if missing)
  • People index: wiki/entities/people/_index.md (create if missing — the canonical roster)
  • Wiki index: wiki/index.md — has an ## Entities section; person rows live there too
  • Log: wiki/log.md — append a ppl entry at the TOP after every add/edit
  • Hot cache: wiki/hot.md — touch only if the person is currently active in recent threads

Why a sub-folder under entities/? Existing entity pages (Your Organization.md) live in wiki/entities/ directly. Keep organizations and tools there; group people under wiki/entities/people/ so the roster is greppable as one set.


Invocation Forms

Form Action
/ppl <Name> <free-text role / context> add (default) — create new person page
/ppl add <Name> <free-text> same as above, explicit
/ppl edit <Name> update existing person page
/ppl list show the roster from _index.md
/ppl lookup <Name or alias> display the person's page

If $ARGUMENTS is empty, show the four forms and ask which one.


Parsing /ppl <Name> <tail>

  1. Split tokens. The Name is the leading run of [A-Z][a-z']+ tokens (capitalized words). Take the first 2 capitalized tokens by default. If only one capitalized token, take 1. If 3+ consecutive capitalized tokens before a lowercase word (e.g. Mary Jane Watson), take 3.
  2. The tail is everything after the name — that's role + relationship + free context.
  3. Heuristics on the tail (do not over-fit, but capture what's obvious):
    • Role — the noun phrase before "in/at/on/of" or before "my". Examples: Security Researcher in my team → role Security Researcher; head of engineering → role Head of Engineering.
    • Relationship to you — look for: my manager, my team, co founder / cofounder / co-founder, cpo, cto, ceo, head of …, peer, report, direct report, reports to me. Map to a short relationship value: manager, teammate, direct-report, cofounder, executive, peer, external. If multiple apply, store the closest to you (e.g. cofounder over executive).
    • Team — capture <role> in my team → team Your Organization unless tail says otherwise.
    • Company — default Your Organization if no other company is named; if the tail names a different company, use that.
  4. Anything unparsed stays as free-form context in the page body. Don't drop it.

Read the full file on GitHub · 289 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. 5d ago First seen · 289 lines · 137 tokens per session scan A 2adb1f7c038b

Subscribe to this mod's changes

ppl is a skill published in the GitHub repository eliransu/digital-brain (1 stars, last pushed 3mo ago), licensed MIT. It adds 137 tokens to every session and 3,056 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

llm-wiki

Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…

praneybehl/llm-wiki-plugin · 221 tokens

llm-wiki

Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).

zosmaai/pi-llm-wiki · 52 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

mindbase

Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…

frankchu91/mindbase-llm-wiki · 105 tokens

setup

Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 15 kernel primitives. Triggers on "/setup", "/setup --advanced", "set up my knowledge system", "create my vault".

agenticnotetaking/arscontexta · 53 tokens

migrate

Scan the project and migrate existing documentation into OKF format. Use when the user wants to populate the knowledge base from existing docs, README, schemas, API specs, runbooks, or any structured project knowledge. Trigger on "migrate to okf", "populate the knowledge base", "scan my docs", "convert docs to okf"…

guhcostan/claude-mega-brain · 147 tokens