What is navegador CLAUDE.md?

Project instructions for navegador, a code-analysis and knowledge-graph tool for AI coding agents. It parses source code into a graph database so agents can inspect relationships in a codebase through an MCP server or Python API.

Understanding the repository, working with its parsers and graph storage, using its command-line tools, and connecting agents to code context through MCP.

It gives an agent the project's architecture, technology choices, and package layout so changes fit the existing system.

How ConflictHQ/navegador configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ConflictHQ/navegador. 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/ConflictHQ/navegador/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ConflictHQ/navegador

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/conflicthq/navegador/claude-md/github.svg)](https://agentmods.dev/instructions/conflicthq/navegador/claude-md)

Your own site

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

Per session 1,057 This file is loaded in full into every session.

When invoked 1,057 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	$0.01057	$0.01057
Opus 5.5	$0.00423	$0.00423
Sonnet 5.5	$0.00211	$0.00211
Haiku 4.5	$0.00106	$0.00106

Measured 5d ago against content hash 4a6ee5e5be39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

navegador 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Navegador — Claude Context

Primary conventions doc: bootstrap.md — read it before writing any code.

What it is

AST + knowledge graph context engine for AI coding agents. Parses codebases into a FalkorDB property graph. Agents query via MCP or Python API.

Stack

Python 3.12+, standalone (no Django dependency)
tree-sitter for multi-language AST parsing (13 languages)
FalkorDB graph DB with falkordblite (embedded via redislite; graph file is a Redis RDB snapshot, not SQLite) for local use
MCP (mcp Python SDK) for AI agent integration (25 tools)
Click + Rich for CLI
Pydantic for data models
Ruff for linting/formatting

Package layout

navegador/
  cli/           — Click commands (50+ subcommands)
  graph/         — GraphStore + schema + queries + migrations + export + mimwell-kg/v1 interchange + transfer (store-to-store copy)
  ingestion/     — RepoIngester + 13 language parsers + optimization
  context/       — ContextLoader + ContextBundle (JSON/markdown)
  mcp/           — MCP server with 25 tools + security hardening
  enrichment/    — FrameworkEnricher base + 8 framework enrichers
  analysis/      — impact, flow tracing, dead code, cycles, test mapping
  intelligence/  — semantic search, community detection, NLP, doc generation
  cluster/       — Redis pub/sub, task queue, locking, sessions, messaging, shard load/unload
  federation.py  — SuperGraphAggregator (repo graphs → central super-graph)
  sdk.py         — Python SDK (Navegador class)
  llm.py         — LLM provider abstraction (Anthropic, OpenAI, Ollama)
  vcs.py         — VCS abstraction (Git, Fossil)
  diff.py        — Git diff → graph impact mapping
  churn.py       — Behavioural coupling from git history
  monorepo.py    — Workspace detection + ingestion
  security.py    — Sensitive content detection + redaction
  config.py      — Layered storage resolution (flags > env > project > user > default)
  server.py      — Native FalkorDB server lifecycle (no Docker)
  inventory.py   — Project discovery + stranded-graph detection
  manual.py      — Packaged docs, offline + over MCP
  docs/          — mkdocs sources, shipped inside the wheel
  explorer/      — HTTP server + browser-based graph visualization

Read the full file on GitHub · 106 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.

5d ago Changed · +1 tokens per session 4a6ee5e5be39
2mo ago First seen · 106 lines · 1,056 tokens per session scan A 8fad62e57201

Subscribe to this mod's changes

navegador CLAUDE.md is an instructions file published in the GitHub repository ConflictHQ/navegador (11 stars, last pushed 6d ago), licensed MIT. It adds 1,057 tokens to every session, about $0.0042 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 2026-08-30.

ai-agents ast code-analysis context-management falkordb knowledge-graph

navegador CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
navegador CLAUDE.mdConflictHQ/navegador	Instructions file	11	6d ago	MIT	A	1,057	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

navegador: Instructions file for Claude Code