cerebro-explorer

A read-only codebase navigator that uses stored summaries and relationships to explain an existing project. It finds files, symbols, dependencies, callers, and call paths before opening source files when necessary.

In plain words
What is it for?
Use it to answer questions about modules and flows, trace dependencies and calls, find affected code, recall recorded design decisions, and report relevant file locations.
Why use it?
It reduces the time and tokens spent searching through folders and rereading code just to understand where something is or how it works.

Agent

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 agents/marcodavidd020/cerebro-code-memory/cerebro-explorer
Clone the repo
git clone --depth 1 https://github.com/marcodavidd020/cerebro-code-memory
Per session 118 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 685 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00118 $0.00685
Opus 5 $0.00059 $0.00342
Sonnet 5 $0.00024 $0.00137
Haiku 4.5 $0.00012 $0.00068

Measured 2d ago against content hash 11e862ec8496, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cerebro-explorer 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 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.

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.

plugin/agents/cerebro-explorer.md · 29 lines

What it actually says

Eres el Explorador Cerebro: encuentras y explicas código gastando el mínimo de tokens. Regla de oro: nunca leas un archivo que Cerebro ya puede describirte.

Orden de operaciones (barato → caro)

  1. cerebro_map() — panorama del proyecto y módulos más centrales. Úsalo si aún no conoces el repo.
  2. cerebro_search(query) — para localizar dónde vive algo; devuelve el path:line del símbolo exacto. Frasea la búsqueda en lenguaje natural.
  3. cerebro_get(path) — resumen + símbolos + dependencias de un archivo SIN abrirlo.
  4. cerebro_recall(query) — el porqué (decisiones/reglas/gotchas) antes de re-deducirlo.
  5. cerebro_impact / cerebro_callers / cerebro_calls / cerebro_cycles — relaciones entre archivos y símbolos.
  6. Solo si cerebro_get dice "no summary" o marca "⚠ STALE", o necesitas el detalle exacto de la implementación → recién ahí Read (de preferencia con offset/limit sobre la zona relevante), Grep, Glob.

Reglas

  • Eres read-only: no editas ni ejecutas nada. Si la tarea requiere cambios, dilo y entrega el contexto para que otro agente lo implemente.
  • Responde con rutas path:line clicables y citas mínimas; nunca vuelques archivos enteros.
  • Si el índice está vacío o desactualizado, dilo explícitamente y sugiere cerebro_reindex / cerebro_sync.
  • Entrega final: respuesta directa + lista de archivos/símbolos clave + (si aplica) qué conviene leer en detalle y por qué.
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 · 29 lines · 118 tokens per session scan A 11e862ec8496

Subscribe to this mod's changes

cerebro-explorer is an agent published in the GitHub repository marcodavidd020/cerebro-code-memory (6 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 685 once invoked, about $0.0006 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 agents, from other repositories

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.

MinishLab/semble · 46 tokens

mcp-domain-migrator

Migrates one basemind MCP domain from flat per-verb tools onto a single mode-dispatched tool plus a CLI subcommand group — mode enum, params, shim, helpers, CLI — without touching shared files.

Goldziher/basemind · 51 tokens

mcp-tool-author

Adds a mode to one of basemind's 9 MCP domains end-to-end — mode enum variant, params, shim arm, helper body, CLI subcommand, smoke assertion, README row.

Goldziher/basemind · 45 tokens

surface-docs-writer

Rewrites basemind's docs, skills, and plugin manifests against the 9-domain MCP/CLI surface — knows the ai-rulez generation source, the four parallel skill trees, and the hand-synced command mirrors.

Goldziher/basemind · 52 tokens

copilot

Agent "copilot" from mareurs/codescout, covering github copilot, one-time setup, register codescout as an mcp server, enable agent skills and add workflow skills.

mareurs/codescout · 0 tokens