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/philipyaz/cos/second-brain-querynpx skills add philipyaz/cos --skill second-brain-querygit 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-query)<a href="https://agentmods.dev/skills/philipyaz/cos/second-brain-query"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/second-brain-query.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 | $0.00134 | $0.01416 |
| Opus 5 | $0.00067 | $0.00708 |
| Sonnet 5 | $0.00027 | $0.00283 |
| Haiku 4.5 | $0.00013 | $0.00142 |
Grade A, and why
second-brain-query 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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Brain — Query (knowledge-only, read-only)
Answer questions by searching and synthesizing knowledge from the domain-split wiki. This skill is read-only — it never writes, edits, or runs commands. It also has no board access: it answers from knowledge, not from open work.
CORE LOOP
1. Determine the domain — work | life | both
From the question, decide which wiki tree(s) to search:
- work — the venture, the role, advisory, work contacts/projects →
work/wiki. - life — trips, health, admin, family, personal logistics →
life/wiki. - both — a question that spans the two (the user themself, the home city, anything
touching
shared/wikientities, or an explicitly cross-cutting question) → searchwork/wikiandlife/wiki, plusshared/wiki.
When unsure, prefer both and let the index tell you which side actually has the answer.
2. Enter through the strong index
Read <domain>/wiki/index.md — the strong index is the entry point. It is a map of
overarching themes, each grouping its concepts, entities, and sources. Find the
theme(s) relevant to the question and the specific [[pages]] listed under them. The
index, not a directory scan, is how you locate the right pages fast.
3. Follow the [[wikilinks]]
Read the pages the index points you to, then follow their [[wikilinks]] to pull in
related context (linked entities, concepts, and source pages). Read enough to answer
thoroughly — but don't read the whole wiki. If the wiki pages don't fully answer, drop to
the relevant <domain>/wiki/sources/ pages for detail; go to raw/ only as a last resort.
4. Surface associated artifacts (CRUCIAL)
For the pages you cite, also surface any associated artifacts — files under
raw/assets/ linked from those pages (the source pages reference preserved attachments via
relative markdown links like ../../raw/assets/<file>). List their paths in your
answer so the user can retrieve the original artifact, not just the synthesized text. If a
cited page links an asset, name 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.
- 4d ago First seen · 108 lines · 134 tokens per session scan A eeb1091e81af
second-brain-query is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 134 tokens to every session and 1,416 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-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
vault-health-batch
Autonomous batch mode for Vault Health findings. Works through orphans, missing backlinks, and tags in batches without asking on every fix.