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 philipyaz/cos --skill second-brain-ingestgit clone --depth 1 https://github.com/philipyaz/cosWrote 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/philipyaz/cos/second-brain-ingest)<a href="https://agentmods.dev/skills/philipyaz/cos/second-brain-ingest"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/second-brain-ingest.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 | $0.00135 | $0.03292 |
| Opus 5 | $0.00068 | $0.01646 |
| Sonnet 5 | $0.00027 | $0.00658 |
| Haiku 4.5 | $0.00014 | $0.00329 |
Grade A, and why
second-brain-ingest 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 yesterday.
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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Brain — Ingest (knowledge-only)
This skill turns one incoming item into durable knowledge in the domain-split wiki. It does one thing: ingest. It does not route to a board, does not create tasks/reminders/events, does not poll Gmail / OpenWhispr / Calendar, and does not own any watermark. It receives marshalled inputs from the MCP ingest route: the inline text of the item, and zero or more absolute file paths to attached on-device files. Work the inputs you are given; do not go looking for more.
The vault is knowledge-only: a fact / context / who-what-why. Never write task
checkboxes (- [ ]) into any page. Open work and to-dos live on the board, which this
skill has no access to and must not invent.
Vault layout
The wiki is split by domain. Each domain has its own self-contained wiki tree:
| Root | When |
|---|---|
work/wiki/ |
Professional knowledge — the venture, the role, advisory, work entities/concepts/sources. |
life/wiki/ |
Personal knowledge — trips, health, admin, personal entities/concepts/sources. |
shared/wiki/ |
Truly-dual entities only — pages referenced by both domains (the user themself, the city they live in). Lives under shared/wiki/entities. |
Each domain tree holds:
<domain>/wiki/index.md— the strong index (see format below) — the entry point.<domain>/wiki/log.md— the append-only ingest log.<domain>/wiki/entities/— people / orgs / products / tools.<domain>/wiki/concepts/— ideas / projects / themes.<domain>/wiki/sources/— one factual page per real source.
Other shared resources at the vault root:
aliases.md— the manual entity-resolution map (surface forms → canonical[[Entity]]).raw/assets/— preserved copies of attached artifacts. Drop attachments intoraw/assets/inside your vault (the path is relative to the vault root, which is this session's cwd).
CORE LOOP
0. Triage — information vs. bloat (do this FIRST)
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.
- yesterday Changed · +47 lines · +19 tokens per session 405f936e8260
- 7d ago First seen · 204 lines · 116 tokens per session scan A 7a2db1231ad6
second-brain-ingest is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 3,292 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
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…
wiki-query
Answer a question using ONLY the existing wiki vault as the knowledge base — no web search, no general LLM knowledge. Reads hot.md first (cheap recent context), then catalog.md to navigate, then drills into specific pages, then optionally semantic-searches the wiki, and synthesizes an answer with citations. Use when…
wiki-fold
Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…
wiki
Bootstrap or check a Karpathy-style "LLM wiki" structure inside an Obsidian vault — a self-maintaining knowledge base where pages reference each other and the LLM keeps it tidy. Sets up catalog.md (curated page catalog), journal.md (append-only operation history), hot.md (recent-context cache), and overview.md…