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 agentmods add skills/eliransu/digital-brain/pplnpx skills add eliransu/digital-brain --skill pplgit clone --depth 1 https://github.com/eliransu/digital-brainWrote 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/eliransu/digital-brain/ppl)<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>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 | $0.00137 | $0.03056 |
| Opus 5 | $0.00068 | $0.01528 |
| Sonnet 5 | $0.00027 | $0.00611 |
| Haiku 4.5 | $0.00014 | $0.00306 |
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.
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## Entitiessection; person rows live there too - Log:
wiki/log.md— append applentry 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 inwiki/entities/directly. Keep organizations and tools there; group people underwiki/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>
- 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. - The tail is everything after the name — that's role + relationship + free context.
- 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→ roleSecurity Researcher;head of engineering→ roleHead 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 shortrelationshipvalue:manager,teammate,direct-report,cofounder,executive,peer,external. If multiple apply, store the closest to you (e.g.cofounderoverexecutive). - Team — capture
<role> in my team→ teamYour Organizationunless tail says otherwise. - Company — default
Your Organizationif no other company is named; if the tail names a different company, use that.
- Role — the noun phrase before "in/at/on/of" or before "my". Examples:
- Anything unparsed stays as free-form
contextin the page body. Don't drop it.
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.
- 5d ago First seen · 289 lines · 137 tokens per session scan A 2adb1f7c038b
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.
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…
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).
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'.
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…"…
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".
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"…