pure-context: Instructions file for Claude Code

CLAUDE.md

pure-context CLAUDE.md is an instructions file for Claude Code from goranocokoljic/pure-context. It costs 43,563 tokens per session, scanned A, original, MIT.

Project instructions for PureContext MCP, a server that indexes source code so agents can retrieve symbols and assess the likely impact and risk of edits.

In plain words
What is it for?
Guiding work on code indexing, symbol retrieval, change-impact analysis, refactoring safety, and the TypeScript server architecture.
Why use it?
They help agents follow the project's required three-layer design and consult its documented rules before making changes.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is goranocokoljic/pure-context's own configuration. It tells Claude Code how to work on pure-context 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 pure-context configures →

Reuse

Borrowing it

Nothing to install: this file belongs to goranocokoljic/pure-context. 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/goranocokoljic/pure-context/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/goranocokoljic/pure-context

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 pure-context CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/goranocokoljic/pure-context/claude-md.svg)](https://agentmods.dev/instructions/goranocokoljic/pure-context/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/goranocokoljic/pure-context/claude-md"><img src="https://agentmods.dev/badge/instructions/goranocokoljic/pure-context/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 43,563 This file is loaded in full into every session.
When invoked 43,563 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 $0.43563 $0.43563
Opus 5 $0.21781 $0.21781
Sonnet 5 $0.08713 $0.08713
Haiku 4.5 $0.04356 $0.04356

Measured 7d ago against content hash 33473c2ee13d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pure-context 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 · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

If you ever need to run python scripts, use python, not python 3.

PureContext MCP — Project Instructions

What This Project Is

PureContext MCP is a Node.js/TypeScript MCP (Model Context Protocol) code-intelligence server for AI agents. It indexes codebases using tree-sitter AST parsing, stores structured symbol metadata in SQLite, and serves two layers: token-efficient retrieval (let agents pull the exact symbols they need instead of reading whole files — the original, benchmarked foundation) and change intelligence (blast radius, temporal co-change, composite per-symbol risk, and refactor-safety checks so an agent can assess the impact and risk of an edit before making it). Retrieval is the foundation; safe autonomous change is the differentiation.

The full product requirements are in docs/PureContext_MCP_PRD_v1.0.docx. Read it before making architectural decisions.


Architecture Rules

Three-Layer Architecture (never violate)

  1. Core (src/core/) — File discovery, content hashing, tree-sitter dispatch, SQLite storage, MCP transport, file watcher. Knows nothing about specific languages or frameworks.
  2. Language Handlers (src/handlers/) — Map file extensions to tree-sitter grammars, define which AST node types are symbols, extract signatures and imports. Each handler is a self-contained module implementing LanguageHandler.
  3. Framework Adapters (src/adapters/) — Domain-specific symbol extraction on top of language handlers. Auto-detected from project config files. Each adapter implements FrameworkAdapter. Optional and composable.

The dependency direction is strictly downward: Adapters → Handlers → Core. Never the reverse.

Key Interfaces

// src/core/types.ts

interface SymbolRecord {
  id: string;                    // Deterministic hash: SHA-256(filePath:name:kind).slice(0,16)
  name: string;
  kind: SymbolKind;
  filePath: string;              // Relative to repo root
  startByte: number;
  endByte: number;
  signature: string;             // One-line signature
  summary: string;               // One-line description
  frameworkMeta?: Record<string, unknown>;
}

type SymbolKind =
  | 'function' | 'class' | 'method' | 'const' | 'type'
  | 'interface' | 'enum' | 'component' | 'composable'
  | 'hook' | 'route' | 'decorator' | 'middleware' | 'property';

interface LanguageHandler {
  extensions(): string[];
  grammarPath(): string;         // Path to .wasm file (null for regex-only handlers)
  extractSymbols(tree: Tree, source: Buffer): SymbolRecord[];
  extractImports(tree: Tree, source: Buffer): ImportRecord[];
  extractDocstring(node: SyntaxNode): string | null;
}

interface FrameworkAdapter {
  name: string;
  detect(projectRoot: string): Promise<boolean>;
  fileFilter(filePath: string): boolean;
  preProcess?(source: Buffer, filePath: string): ProcessedBlock[];
  extractFrameworkSymbols(tree: Tree, source: Buffer, filePath: string): SymbolRecord[];
  enrichMetadata?(symbol: SymbolRecord): SymbolRecord;
}

Read the full file on GitHub · 410 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 · 410 lines · 43,563 tokens per session scan A 33473c2ee13d

Subscribe to this mod's changes

pure-context CLAUDE.md is an instructions file published in the GitHub repository goranocokoljic/pure-context (7 stars, last pushed 10d ago), licensed MIT. It adds 43,563 tokens to every session, about $0.2178 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 · 5,182 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