What is echowiki CLAUDE.md?

Project-specific instructions for echowiki, an OpenKB-for-Obsidian application that turns recordings and text files into a linked knowledge base in Obsidian, a note-taking app.

Use it when adding or changing echowiki features, especially the raw-to-wiki compilation pipeline, Markdown pages, and TypeScript or Node code.

It gives the coding agent the project's architecture, tools, coding rules, and required work order so changes fit the existing implementation.

How mohammadmaso/echowiki configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mohammadmaso/echowiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mohammadmaso/echowiki/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mohammadmaso/echowiki

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mohammadmaso/echowiki/claude-md/github.svg)](https://agentmods.dev/instructions/mohammadmaso/echowiki/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mohammadmaso/echowiki/claude-md"><img src="https://agentmods.dev/badge/instructions/mohammadmaso/echowiki/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mohammadmaso/echowiki/claude-md"><img src="https://agentmods.dev/badge/instructions/mohammadmaso/echowiki/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,170 This file is loaded in full into every session.

When invoked 1,170 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01170	$0.01170
Opus 5.5	$0.00468	$0.00468
Sonnet 5.5	$0.00234	$0.00234
Haiku 4.5	$0.00117	$0.00117

Measured 2mo ago against content hash f842f18f3871, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

echowiki CLAUDE.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 2mo 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.

CLAUDE.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Context & Rules — OpenKB-for-Obsidian (Vercel AI SDK)

What this project is

A full reimplementation of VectifyAI/OpenKB — an open-source LLM Knowledge Base compiler — built with the Vercel AI SDK (TypeScript/Node) instead of OpenKB's original Python stack (OpenAI Agents SDK + LiteLLM).

A single raw/ folder is the universal ingestion point: voice recordings (transcribed via STT) and manually authored/dropped Markdown/text files both land there and are compiled identically. The wiki compiler compiles everything in raw/ into a structured, interlinked wiki/ — summaries, concept pages, entity pages, cross-links — with OKF-schema frontmatter, viewable natively as an Obsidian vault.

See 01-PRD.md and 02-TECH-SPEC.md for full product/technical context. Follow 03-TASKS.md task-by-task; do not skip ahead or bundle multiple tasks into one change.

Reference Implementation

Treat VectifyAI/OpenKB as the architectural reference. Key concepts to preserve when porting to Mastra:

The raw/ → wiki/ compilation pipeline, and the wiki/ folder shape: index.md, log.md, AGENTS.md, sources/, summaries/, concepts/, entities/, explorations/, reports/.
The compilation steps per new document: summary → read existing concepts/entities → create/update concepts → create/update entities → update index/log.
wiki/AGENTS.md as the LLM's own instruction manual for wiki structure/conventions, read from disk at runtime (so edits take effect immediately, no redeploy).
OKF-schema YAML frontmatter on every generated page.
Obsidian-native output: plain Markdown + [[wikilinks]], no proprietary format.

Tech Stack

Vercel AI SDK (ai + @ai-sdk/openai) for LLM calls — compilation runs in-process inside the Obsidian plugin (no child process / HTTP server).
Node-native file watching (chokidar or fs.watch) as the functional analog of upstream's watchdog-based openkb watch.
HTTP calls to user-configured, OpenAI-compatible STT and LLM endpoints — no hardcoded provider.
Voice capture UI: Obsidian plugin (Obsidian Plugin API) if integrated into Obsidian directly, or a standalone companion app if decoupled — this is still an open decision (see PRD open questions); do not assume one without confirming.

Read the full file on GitHub · 50 lines

Changes

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.

2mo ago First seen · 50 lines · 1,170 tokens per session scan A f842f18f3871

Subscribe to this mod's changes

echowiki CLAUDE.md is an instructions file published in the GitHub repository mohammadmaso/echowiki (10 stars, last pushed 4mo ago), licensed MIT. It adds 1,170 tokens to every session, about $0.0047 per session on Opus 5.5. 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.

echowiki CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
echowiki CLAUDE.mdmohammadmaso/echowiki	Instructions file	10	4mo ago	MIT	A	1,170	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

echowiki: Instructions file for Claude Code