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/the-sid-dani/second-brain-os/os-guidenpx skills add the-sid-dani/second-brain-os --skill os-guidegit clone --depth 1 https://github.com/the-sid-dani/second-brain-osWrote 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/the-sid-dani/second-brain-os/os-guide)<a href="https://agentmods.dev/skills/the-sid-dani/second-brain-os/os-guide"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/os-guide.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 | $0.00183 | $0.06491 |
| Opus 5 | $0.00092 | $0.03245 |
| Sonnet 5 | $0.00037 | $0.01298 |
| Haiku 4.5 | $0.00018 | $0.00649 |
Grade B, and why
os-guide scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
| All available skills | `find -L .claude/skills -mindepth 2 -maxdepth 2 -name SKILL.md` then read each frontmatter `description:` line | Follow symlinks, validate frontmatter, and never hardcode the list | How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
os-guide
Runtime-read librarian over the second-brain OS's canonical source files. Answers "how does X work in this OS?" without ever embedding facts that could drift. Every response carries file:line citations.
Before you begin: read the Configuration section in root CLAUDE.md (starts ~line 50; locate via grep -n "^## Configuration" — it moves as sections are added). Path tokens like <workspace.root>, <workspace.projects>, <assistant.name> resolve from there — don't hardcode them in answers.
⚠️ Meta-instruction (for Claude reading this skill)
If you are about to give an OS-shaped answer from memory rather than reading the canonical source — STOP and invoke this skill instead. That includes any answer that contains:
- A workspace path (e.g.,
<workspace.root>/...) - A Configuration token value (
workspace.projects,user.email,assistant.name, etc.) - A claim about a skill's behavior or scope
- A claim that a tool is or isn't installed
- A schema field (contacts, design systems, project frontmatter)
- A locked design decision (if your fork maintains a design-log file)
Memory drifts. Canonical files don't. This skill exists to make the latter cheap to consult.
This rule mirrors the contact-no-fabrication discipline in the user's auto-memory (feedback_contact_scaffolding.md).
Why this exists
The OS has seven+ canonical sources (CLAUDE.md, README.md, SOUL.md, USER.md, IDENTITY.md, TOOLS.md, contacts/README.md, plus individual SKILL.md files — and your own design log if you keep one). Without /os-guide, answering "where does X live?" or "what's the rule about Y?" is a manual ritual of grep + cat + remembering which file owns which topic.
The naive alternative — encoding the answers in a tutorial-style skill body — fails the moment any canonical source drifts. The core principle this skill enforces: explainer skills MUST be runtime-read librarians, not textbooks. Reference, don't reproduce (per SOUL.md Operating Principles).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 425 lines · 183 tokens per session scan B c40ab45c9812
os-guide is a skill published in the GitHub repository the-sid-dani/second-brain-os (2 stars, last pushed 28d ago), licensed MIT. It adds 183 tokens to every session and 6,491 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
follower-onboard
Onboard a NEW family/team machine as a FOLLOWER-CONSUMER joining the multi-machine Claude+vault network. A follower READS the shared vault + canon + skills + memory as RECEIVE- ONLY data, runs nothing heavy locally (no RAG/reindex/GPU), and the hub never pushes executable hooks to it. Trigger on "/follower-onboard "…
claudeai-sync
One-command incremental sync of a claude.ai WEB account into the Obsidian vault — pull only new/changed chats, fold them in as notes (idempotent, never overwrites curated ones), extract artifacts as first-class notes, concept-link the new artifacts, refresh the RAG index + dashboard. Trigger on "/claudeai-sync", "pull…
chat-search
Search INSIDE past Claude Code sessions (the episodic "book of chats" index) — find which previous session discussed a topic, and continue it with one command. Uses a SEPARATE session index, NOT the curated-knowledge RAG, so raw chat noise never pollutes the distilled brain. Trigger on "/chat-search", "which chat…
five-hard
Five Hard Questions — monthly (or on demand) the second brain ITSELF asks the owner 5 hard questions about their own long-held beliefs and codex entries that haven't been revisited in a while. Prevents assumptions from fossilizing. Trigger on "/five-hard", "challenge my beliefs", "pressure-test my views". Part of the…
intake
Rule intake: one pass routes a new rule/preference/policy edit into ALL the right homes (always-loaded canon, memory, the behavioral Bible, a skill, a hook) and leaves a trace in the always-loaded layer so parallel processes see it on their own. Trigger on "/intake", "record this rule", "route this to its homes".…
canon-revision
Full structural REVISION of an always-loaded rules file (CLAUDE.md / MEMORY.md): build a TOP block of the most important rules + numbered categories, move rule bodies verbatim (a script moves bytes and proves 0 losses; the LLM decides only the mapping), fold heavy mechanics into trigger+gist+pointer form, then guards…