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 instructions/epicsagas/alcove/agents-mdgit clone --depth 1 https://github.com/epicsagas/alcoveWrote 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/instructions/epicsagas/alcove/agents-md)<a href="https://agentmods.dev/instructions/epicsagas/alcove/agents-md"><img src="https://agentmods.dev/badge/instructions/epicsagas/alcove/agents-md.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 | $0.01840 | $0.01840 |
| Opus 5 | $0.00920 | $0.00920 |
| Sonnet 5 | $0.00368 | $0.00368 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
alcove AGENTS.md 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Purpose
This repository serves three roles:
- Obsidian vault (Second Brain) — ZK + PARA + LYT hybrid knowledge management system
- Alcove docs root — private project documentation served to AI agents via the
alcoveMCP server - Git repository — versioned with Conventional Commits, remote:
[email protected]:epicsagas/alcove-docs.git
Documents here must never be copied into public project repos.
Actual Location
$VAULT_PATH — accessed by both obsidian-forge and alcove MCP server.
Structure
├── 00-Inbox/ # Capture zone (obsidian-forge AI classification target)
├── 01-Projects/ # Project hub MOC (Dataview queries, no project folders here)
├── 02-Areas/ # Ongoing interest areas (Rust, MCP, AI, Fintech, DevOps, OSS)
├── 03-Resources/ # Reference materials (AWS, Laws-Of-Software-Engineering, etc.)
├── 10-Zettelkasten/ # Permanent concept notes (layer/wiki tagged, 300+ chars)
├── 99-Archives/
│ └── projects/ # ALL project doc folders live here
│ ├── alcove/ # alcove MCP server project docs
│ ├── obsidian-forge/ # obsidian-forge daemon project docs
│ ├── collet/ # ... and all other active/inactive projects
│ └── ...
├── _template/ # Template for new project docs
├── Home.md # Vault dashboard / root MOC
├── TAGGING.md # Tagging and frontmatter conventions
└── vault.toml # Per-vault obsidian-forge config
Project doc folders live in 99-Archives/projects/ — not at the vault root. Do not move them to 01-Projects/.
Karpathy 3-Layer Architecture
| Layer | Location | Content | Automation |
|---|---|---|---|
| Raw | 99-Archives/projects/, 00-Inbox/, 02-Areas/ |
Project docs, captured notes, area notes | of process-all, git sync |
| Wiki | 10-Zettelkasten/ |
Refined atomic concept notes (300+ chars) | Manual curation + of strengthen-graph |
| Graph | Wikilinks across all layers | Connections between Raw and Wiki | of strengthen-graph |
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 · 154 lines · 1,840 tokens per session scan A ed0cc313f442
alcove AGENTS.md is an instructions file published in the GitHub repository epicsagas/alcove (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,840 tokens to every session, about $0.0092 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 2026-08-30.
Other instructions, from other repositories
mcp-markdown-vault CLAUDE.md
Instructions for wirux/mcp-markdown-vault, covering claude.md, project overview, development commands, install dependencies and build (compiles to dist/, excludes test files).
auto-knowledge-base CLAUDE.md
Claude Code instructions for guyeyouhun/auto-knowledge-base, covering 自主知识库 (auto knowledge base), 当前状态, 核心设计原则, 知识类型 and 信任级别.
Soroka CLAUDE.md
Instructions for AndyShaman/Soroka, covering soroka and session-start rule.
fpf-memory AGENTS.md
AGENTS.md instructions for venikman/fpf-memory, covering fpf reference mcp usage, dual runtime (hosted deploy + local full), codex verification rule, operational cli workflows and learned user preferences.
fpf-memory CLAUDE.md
Claude Code instructions for venikman/fpf-memory, covering claude.md — operating mandate for fpf-memory, still confirm — the narrow exceptions and lesson logged 2026-07-06.
mindcache CLAUDE.md
Instructions for augmnt/mindcache, covering mindcache, project structure, server package (packages/server/), commands and build.