agentmods.dev

CodeCortex CLAUDE.md

Project instructions for CodeCortex, a codebase knowledge layer that analyzes a project’s structure, dependencies, symbols, and change history for AI agents. It stores information in files organized by how often it is needed.

In plain words
What is it for?
Use it when developing or maintaining CodeCortex, its TypeScript architecture, knowledge files, code analysis, CLI, or MCP server.
Why use it?
It helps agents understand an unfamiliar codebase before editing it, including which files are connected and where changes may be risky. The instructions also describe CodeCortex’s command-line and MCP interfaces.

Instructions file

7 4mo ago A scan 1,942 tokens original MIT
View the source file rushikeshmore/CodeCortex
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/rushikeshmore/codecortex/claude-md
Clone the repo
git clone --depth 1 https://github.com/rushikeshmore/CodeCortex
Per session 1,942 This file is loaded in full into every session.
When invoked 1,942 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01942 $0.01942
Opus 5 $0.00971 $0.00971
Sonnet 5 $0.00388 $0.00388
Haiku 4.5 $0.00194 $0.00194

Measured 2d ago against content hash 7d5b78d41898, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CodeCortex CLAUDE.md scanned grade A 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 2d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Key deps:** node:path, node:fs, simple-git, node:child_process, commander, +9 more
CLAUDE.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeCortex

Persistent codebase knowledge layer for AI agents. Pre-builds architecture, dependency, coupling, and risk knowledge so agents skip the cold start and go straight to the right files.

Stack

  • TypeScript, ESM ("type": "module")
  • tree-sitter (native N-API) + 27 language grammar packages
  • @modelcontextprotocol/sdk - MCP server (stdio transport)
  • commander - CLI (init, serve, update, inject, status, symbols, search, modules, hotspots, hook, upgrade)
  • simple-git - git integration + temporal analysis
  • zod - schema validation for LLM analysis results
  • yaml - cortex.yaml manifest
  • glob - file discovery

Architecture

Three-tier knowledge storage in .codecortex/ flat files:

  • HOT (always loaded): cortex.yaml, constitution.md, overview.md, graph.json, symbols.json, temporal.json
  • WARM (per-module): modules/*.md
  • COLD (on-demand): decisions/.md, sessions/.md, patterns.md

Hybrid extraction:

  • Tree-sitter native N-API → symbols (name, kind, signature, startLine, endLine, exported), imports, exports, call edges
  • Host LLM → module summaries, decisions, patterns, session diffs

Six Knowledge Layers

  1. Structural (graph.json + symbols.json) - modules, deps, entry points, symbol index
  2. Semantic (modules/*.md) - what each module DOES
  3. Temporal (temporal.json) - git co-change coupling, hotspots, bug archaeology
  4. Decisions (decisions/*.md) - WHY things are built this way
  5. Patterns (patterns.md) - HOW code is written here
  6. Sessions (sessions/*.md) - what CHANGED between sessions

Scripts

  • npm run dev - watch mode development
  • npm run build - tsup build to dist/
  • npm run test - vitest
  • npm run lint - tsc --noEmit

CLI

  • codecortex init - discover + extract + temporal analysis → write .codecortex/
  • codecortex serve - start MCP server
  • codecortex update - re-extract changed files → update modules
  • codecortex status - knowledge freshness, stale modules, symbol counts
  • codecortex symbols [query] - browse and filter the symbol index
  • codecortex search <query> - search across all knowledge files
  • codecortex modules [name] - list modules or deep-dive into one
  • codecortex inject - regenerate inline context in CLAUDE.md and agent config files
  • codecortex hotspots - files ranked by risk (churn + coupling + bugs)
  • codecortex hook install|uninstall|status - manage git hooks for auto-update
  • codecortex upgrade - check for and install latest version

Read the full file on GitHub · 151 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. 2d ago First seen · 151 lines · 1,942 tokens per session scan A 7d5b78d41898

Subscribe to this mod's changes

CodeCortex CLAUDE.md is an instructions file published in the GitHub repository rushikeshmore/CodeCortex (7 stars, last pushed 4mo ago), licensed MIT. It adds 1,942 tokens to every session, about $0.0097 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AILanguagesPlanningai-agentsclaude-codecode-analysisdeveloper-toolsmodel-context-protocoltypescript
Related

Other instructions, from other repositories

now-sdk-ext-mcp CLAUDE.md

Instructions for sonisoft-cnanda/now-sdk-ext-mcp, covering now-sdk-ext-mcp, project overview, architecture, directory structure and sibling projects.

sonisoft-cnanda/now-sdk-ext-mcp · 2,236 tokens

mistral-mcp CLAUDE.md

Instructions for Swih/mistral-mcp, covering claude.md — mistral-mcp, 1. identité du projet, 2. règles dures (ne pas transgresser), 3. layout & responsabilités and 4. conventions de code.

Swih/mistral-mcp · 3,342 tokens

velog_mcp AGENTS.md

Instructions for seongwon030/velog_mcp, covering agents.md, 프로젝트 개요, 스택과 명령어, 아키텍처 and api와 동작 메모.

seongwon030/velog_mcp · 1,560 tokens

mcp-local-llm AGENTS.md

Instructions for aplaceforallmystuff/mcp-local-llm, covering agents.md - mcp-local-llm, tech stack, architecture, development commands and environment variables.

aplaceforallmystuff/mcp-local-llm · 377 tokens

miftah AGENTS.md

Instructions for mohanagy/miftah, covering miftah agent instructions, madar, codex cli profile and release protocol.

mohanagy/miftah · 1,438 tokens

mcp CLAUDE.md

Instructions for fouradata/mcp, covering using the foura mcp with claude, claude code, claude desktop and what you get.

fouradata/mcp · 439 tokens