exocortex: Instructions file for Claude Code

CLAUDE.md

exocortex CLAUDE.md is an instructions file for Claude Code from janos-gyorgy/exocortex. It costs 702 tokens per session, scanned A, original, MIT.

A set of instructions for AI agents working in Exocortex, a shared Markdown-based human and AI memory vault.

In plain words
What is it for?
Use it when maintaining Exocortex notes, checking the Markdown vault against its index, adding linked knowledge, or following its nightly cleanup routine.
Why use it?
It defines how to search, update, link, index, and review notes so the vault stays consistent and useful over time.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is janos-gyorgy/exocortex's own configuration. It tells Claude Code how to work on exocortex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything exocortex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to janos-gyorgy/exocortex. 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/janos-gyorgy/exocortex/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/janos-gyorgy/exocortex

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.

agentmods badge for exocortex CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/janos-gyorgy/exocortex/claude-md.svg)](https://agentmods.dev/instructions/janos-gyorgy/exocortex/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/janos-gyorgy/exocortex/claude-md"><img src="https://agentmods.dev/badge/instructions/janos-gyorgy/exocortex/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 702 This file is loaded in full into every session.
When invoked 702 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00702 $0.00702
Opus 5 $0.00351 $0.00351
Sonnet 5 $0.00140 $0.00140
Haiku 4.5 $0.00070 $0.00070

Measured 7d ago against content hash 93dbfd8451c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

exocortex 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 7d 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Operating contract for agents in the exocortex

You are an agent working inside a shared human+AI memory. The markdown vault is the source of truth. You are a librarian and gardener, not a hoarder.

Golden rules

  1. Markdown is canonical. Never treat the SQLite index as authoritative. If files and index disagree, the files win. Drift is detected (exo status / vault_status, Synced/OutOfSync) and auto-reconciled by git hooks (.githooks/, post-commit + post-merge). If a checkout lacks the hooks (git config core.hooksPath .githooks), fall back to exo index by hand.
  2. Every write is a reviewable git diff. Make small, atomic commits. Set the agent: frontmatter field on notes you author or materially edit.
  3. Search before you write. Call hybrid_search first. If a near-duplicate exists, extend or link it — do not create a parallel note.
  4. Link, don't pile. A new note with no relations is half-done. Add at least one relations: edge (note IDs) and at least one body [[Wikilink]].
  5. Explain non-trivial changes. One line in the commit / note summary: is enough. No ceremony.

Tools you have

  • Retrieval & graph (this repo's MCP server exocortex): hybrid_search, get_backlinks, get_neighbors, list_orphans, list_hubs, garden_report, reindex, vault_status, collide (distant-pair serendipity; a "no connection" result is valid — only log genuine hits to claude-sparks).
  • Note CRUD (Basic Memory MCP): create/read/edit/move notes. Use it for writes.
  • Shell (Claude Code): exo CLI, git, ripgrep.

Note shape (see vault/templates/note.md)

  • id is a stable slug. type ∈ concept|claim|source|project|person|log|moc.
  • Relations reference note IDs as plain strings. Wikilinks [[...]] go in the body only (YAML mangles brackets).
  • Keep summary: to one line and current.

Routine: nightly gardener

  1. garden_report → review orphans, hubs, link suggestions, summary candidates.
  2. Propose concrete edits. For each: search to confirm, then write via Basic Memory, then reindex.
  3. Promote dense hubs to type: moc when a domain has >~8 connected notes.
  4. Commit with message garden: <what changed>.

Read the full file on GitHub · 51 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. 7d ago First seen · 51 lines · 702 tokens per session scan A 93dbfd8451c7

Subscribe to this mod's changes

exocortex CLAUDE.md is an instructions file published in the GitHub repository janos-gyorgy/exocortex (0 stars, last pushed 2mo ago), licensed MIT. It adds 702 tokens to every session, about $0.0035 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

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 · 5,153 tokens

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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 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

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

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