echowiki CLAUDE.md

echowiki CLAUDE.md is an instructions file for coding agents from mohammadmaso/echowiki. It costs 1,170 tokens per session, scanned A, original, MIT.

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.

In plain words
What is it for?
Use it when adding or changing echowiki features, especially the raw-to-wiki compilation pipeline, Markdown pages, and TypeScript or Node code.
Why use it?
It gives the coding agent the project's architecture, tools, coding rules, and required work order so changes fit the existing implementation.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/mohammadmaso/echowiki/claude-md
Clone the repo
git clone --depth 1 https://github.com/mohammadmaso/echowiki

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.

agentmods badge for echowiki CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mohammadmaso/echowiki/claude-md.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01170 $0.01170
Opus 5 $0.00585 $0.00585
Sonnet 5 $0.00234 $0.00234
Haiku 4.5 $0.00117 $0.00117

Measured 5d ago against content hash f842f18f3871, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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.

  1. 5d 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 2mo ago), licensed MIT. It adds 1,170 tokens to every session, about $0.0059 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens